[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-jetbrains-mcp-builder":3,"mdc-9yrik7-key":33,"related-repo-jetbrains-mcp-builder":1305,"related-org-jetbrains-mcp-builder":1429},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"mcp-builder","build MCP servers for external services","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"jetbrains","JetBrains","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fjetbrains.png",[12,16,19],{"name":13,"slug":14,"type":15},"MCP","mcp","tag",{"name":17,"slug":18,"type":15},"Engineering","engineering",{"name":20,"slug":21,"type":15},"API Development","api-development",252,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills","2026-07-13T06:42:02.020877","Complete terms in LICENSE.txt",17,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Curated agent skills collection verified by JetBrains","https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills\u002Ftree\u002FHEAD\u002Fmcp-builder","---\nname: mcp-builder\ndescription: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).\nlicense: Complete terms in LICENSE.txt\nmetadata:\n  short-description: \"Build high-quality MCP servers\"\n  author: Anthropic\n  source: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fmcp-builder\n---\n\n# MCP Server Development Guide\n\n## Overview\n\nCreate MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.\n\n---\n\n# Process\n\n## 🚀 High-Level Workflow\n\nCreating a high-quality MCP server involves four main phases:\n\n### Phase 1: Deep Research and Planning\n\n#### 1.1 Understand Modern MCP Design\n\n**API Coverage vs. Workflow Tools:**\nBalance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.\n\n**Tool Naming and Discoverability:**\nClear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming.\n\n**Context Management:**\nAgents benefit from concise tool descriptions and the ability to filter\u002Fpaginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.\n\n**Actionable Error Messages:**\nError messages should guide agents toward solutions with specific suggestions and next steps.\n\n#### 1.2 Study MCP Protocol Documentation\n\n**Navigate the MCP specification:**\n\nStart with the sitemap to find relevant pages: `https:\u002F\u002Fmodelcontextprotocol.io\u002Fsitemap.xml`\n\nThen fetch specific pages with `.md` suffix for markdown format (e.g., `https:\u002F\u002Fmodelcontextprotocol.io\u002Fspecification\u002Fdraft.md`).\n\nKey pages to review:\n- Specification overview and architecture\n- Transport mechanisms (streamable HTTP, stdio)\n- Tool, resource, and prompt definitions\n\n#### 1.3 Study Framework Documentation\n\n**Recommended stack:**\n- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)\n- **Transport**: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.\n\n**Load framework documentation:**\n\n- **MCP Best Practices**: [📋 View Best Practices](.\u002Freference\u002Fmcp_best_practices.md) - Core guidelines\n\n**For TypeScript (recommended):**\n- **TypeScript SDK**: Use WebFetch to load `https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\u002Fmain\u002FREADME.md`\n- [⚡ TypeScript Guide](.\u002Freference\u002Fnode_mcp_server.md) - TypeScript patterns and examples\n\n**For Python:**\n- **Python SDK**: Use WebFetch to load `https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Fpython-sdk\u002Fmain\u002FREADME.md`\n- [🐍 Python Guide](.\u002Freference\u002Fpython_mcp_server.md) - Python patterns and examples\n\n#### 1.4 Plan Your Implementation\n\n**Understand the API:**\nReview the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.\n\n**Tool Selection:**\nPrioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.\n\n---\n\n### Phase 2: Implementation\n\n#### 2.1 Set Up Project Structure\n\nSee language-specific guides for project setup:\n- [⚡ TypeScript Guide](.\u002Freference\u002Fnode_mcp_server.md) - Project structure, package.json, tsconfig.json\n- [🐍 Python Guide](.\u002Freference\u002Fpython_mcp_server.md) - Module organization, dependencies\n\n#### 2.2 Implement Core Infrastructure\n\nCreate shared utilities:\n- API client with authentication\n- Error handling helpers\n- Response formatting (JSON\u002FMarkdown)\n- Pagination support\n\n#### 2.3 Implement Tools\n\nFor each tool:\n\n**Input Schema:**\n- Use Zod (TypeScript) or Pydantic (Python)\n- Include constraints and clear descriptions\n- Add examples in field descriptions\n\n**Output Schema:**\n- Define `outputSchema` where possible for structured data\n- Use `structuredContent` in tool responses (TypeScript SDK feature)\n- Helps clients understand and process tool outputs\n\n**Tool Description:**\n- Concise summary of functionality\n- Parameter descriptions\n- Return type schema\n\n**Implementation:**\n- Async\u002Fawait for I\u002FO operations\n- Proper error handling with actionable messages\n- Support pagination where applicable\n- Return both text content and structured data when using modern SDKs\n\n**Annotations:**\n- `readOnlyHint`: true\u002Ffalse\n- `destructiveHint`: true\u002Ffalse\n- `idempotentHint`: true\u002Ffalse\n- `openWorldHint`: true\u002Ffalse\n\n---\n\n### Phase 3: Review and Test\n\n#### 3.1 Code Quality\n\nReview for:\n- No duplicated code (DRY principle)\n- Consistent error handling\n- Full type coverage\n- Clear tool descriptions\n\n#### 3.2 Build and Test\n\n**TypeScript:**\n- Run `npm run build` to verify compilation\n- Test with MCP Inspector: `npx @modelcontextprotocol\u002Finspector`\n\n**Python:**\n- Verify syntax: `python -m py_compile your_server.py`\n- Test with MCP Inspector\n\nSee language-specific guides for detailed testing approaches and quality checklists.\n\n---\n\n### Phase 4: Create Evaluations\n\nAfter implementing your MCP server, create comprehensive evaluations to test its effectiveness.\n\n**Load [✅ Evaluation Guide](.\u002Freference\u002Fevaluation.md) for complete evaluation guidelines.**\n\n#### 4.1 Understand Evaluation Purpose\n\nUse evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.\n\n#### 4.2 Create 10 Evaluation Questions\n\nTo create effective evaluations, follow the process outlined in the evaluation guide:\n\n1. **Tool Inspection**: List available tools and understand their capabilities\n2. **Content Exploration**: Use READ-ONLY operations to explore available data\n3. **Question Generation**: Create 10 complex, realistic questions\n4. **Answer Verification**: Solve each question yourself to verify answers\n\n#### 4.3 Evaluation Requirements\n\nEnsure each question is:\n- **Independent**: Not dependent on other questions\n- **Read-only**: Only non-destructive operations required\n- **Complex**: Requiring multiple tool calls and deep exploration\n- **Realistic**: Based on real use cases humans would care about\n- **Verifiable**: Single, clear answer that can be verified by string comparison\n- **Stable**: Answer won't change over time\n\n#### 4.4 Output Format\n\nCreate an XML file with this structure:\n\n```xml\n\u003Cevaluation>\n  \u003Cqa_pair>\n    \u003Cquestion>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?\u003C\u002Fquestion>\n    \u003Canswer>3\u003C\u002Fanswer>\n  \u003C\u002Fqa_pair>\n\u003C!-- More qa_pairs... -->\n\u003C\u002Fevaluation>\n```\n\n---\n\n# Reference Files\n\n## 📚 Documentation Library\n\nLoad these resources as needed during development:\n\n### Core MCP Documentation (Load First)\n- **MCP Protocol**: Start with sitemap at `https:\u002F\u002Fmodelcontextprotocol.io\u002Fsitemap.xml`, then fetch specific pages with `.md` suffix\n- [📋 MCP Best Practices](.\u002Freference\u002Fmcp_best_practices.md) - Universal MCP guidelines including:\n  - Server and tool naming conventions\n  - Response format guidelines (JSON vs Markdown)\n  - Pagination best practices\n  - Transport selection (streamable HTTP vs stdio)\n  - Security and error handling standards\n\n### SDK Documentation (Load During Phase 1\u002F2)\n- **Python SDK**: Fetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Fpython-sdk\u002Fmain\u002FREADME.md`\n- **TypeScript SDK**: Fetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\u002Fmain\u002FREADME.md`\n\n### Language-Specific Implementation Guides (Load During Phase 2)\n- [🐍 Python Implementation Guide](.\u002Freference\u002Fpython_mcp_server.md) - Complete Python\u002FFastMCP guide with:\n  - Server initialization patterns\n  - Pydantic model examples\n  - Tool registration with `@mcp.tool`\n  - Complete working examples\n  - Quality checklist\n\n- [⚡ TypeScript Implementation Guide](.\u002Freference\u002Fnode_mcp_server.md) - Complete TypeScript guide with:\n  - Project structure\n  - Zod schema patterns\n  - Tool registration with `server.registerTool`\n  - Complete working examples\n  - Quality checklist\n\n### Evaluation Guide (Load During Phase 4)\n- [✅ Evaluation Guide](.\u002Freference\u002Fevaluation.md) - Complete evaluation creation guide with:\n  - Question creation guidelines\n  - Answer verification strategies\n  - XML format specifications\n  - Example questions and answers\n  - Running an evaluation with the provided scripts\n",{"data":34,"body":39},{"name":4,"description":6,"license":25,"metadata":35},{"short-description":36,"author":37,"source":38},"Build high-quality MCP servers","Anthropic","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fmcp-builder",{"type":40,"children":41},"root",[42,51,58,64,68,74,80,85,92,99,110,137,147,157,163,171,182,203,208,228,234,242,265,273,295,303,333,341,370,376,386,396,399,405,411,416,437,443,448,471,477,482,490,508,516,550,558,576,584,607,615,659,662,668,674,679,702,708,716,743,751,770,775,778,784,789,805,811,816,822,827,871,877,882,945,951,956,1032,1035,1041,1047,1052,1058,1123,1129,1159,1165,1253,1259,1299],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"mcp-server-development-guide",[48],{"type":49,"value":50},"text","MCP Server Development Guide",{"type":43,"tag":52,"props":53,"children":55},"h2",{"id":54},"overview",[56],{"type":49,"value":57},"Overview",{"type":43,"tag":59,"props":60,"children":61},"p",{},[62],{"type":49,"value":63},"Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.",{"type":43,"tag":65,"props":66,"children":67},"hr",{},[],{"type":43,"tag":44,"props":69,"children":71},{"id":70},"process",[72],{"type":49,"value":73},"Process",{"type":43,"tag":52,"props":75,"children":77},{"id":76},"high-level-workflow",[78],{"type":49,"value":79},"🚀 High-Level Workflow",{"type":43,"tag":59,"props":81,"children":82},{},[83],{"type":49,"value":84},"Creating a high-quality MCP server involves four main phases:",{"type":43,"tag":86,"props":87,"children":89},"h3",{"id":88},"phase-1-deep-research-and-planning",[90],{"type":49,"value":91},"Phase 1: Deep Research and Planning",{"type":43,"tag":93,"props":94,"children":96},"h4",{"id":95},"_11-understand-modern-mcp-design",[97],{"type":49,"value":98},"1.1 Understand Modern MCP Design",{"type":43,"tag":59,"props":100,"children":101},{},[102,108],{"type":43,"tag":103,"props":104,"children":105},"strong",{},[106],{"type":49,"value":107},"API Coverage vs. Workflow Tools:",{"type":49,"value":109},"\nBalance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.",{"type":43,"tag":59,"props":111,"children":112},{},[113,118,120,127,129,135],{"type":43,"tag":103,"props":114,"children":115},{},[116],{"type":49,"value":117},"Tool Naming and Discoverability:",{"type":49,"value":119},"\nClear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., ",{"type":43,"tag":121,"props":122,"children":124},"code",{"className":123},[],[125],{"type":49,"value":126},"github_create_issue",{"type":49,"value":128},", ",{"type":43,"tag":121,"props":130,"children":132},{"className":131},[],[133],{"type":49,"value":134},"github_list_repos",{"type":49,"value":136},") and action-oriented naming.",{"type":43,"tag":59,"props":138,"children":139},{},[140,145],{"type":43,"tag":103,"props":141,"children":142},{},[143],{"type":49,"value":144},"Context Management:",{"type":49,"value":146},"\nAgents benefit from concise tool descriptions and the ability to filter\u002Fpaginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.",{"type":43,"tag":59,"props":148,"children":149},{},[150,155],{"type":43,"tag":103,"props":151,"children":152},{},[153],{"type":49,"value":154},"Actionable Error Messages:",{"type":49,"value":156},"\nError messages should guide agents toward solutions with specific suggestions and next steps.",{"type":43,"tag":93,"props":158,"children":160},{"id":159},"_12-study-mcp-protocol-documentation",[161],{"type":49,"value":162},"1.2 Study MCP Protocol Documentation",{"type":43,"tag":59,"props":164,"children":165},{},[166],{"type":43,"tag":103,"props":167,"children":168},{},[169],{"type":49,"value":170},"Navigate the MCP specification:",{"type":43,"tag":59,"props":172,"children":173},{},[174,176],{"type":49,"value":175},"Start with the sitemap to find relevant pages: ",{"type":43,"tag":121,"props":177,"children":179},{"className":178},[],[180],{"type":49,"value":181},"https:\u002F\u002Fmodelcontextprotocol.io\u002Fsitemap.xml",{"type":43,"tag":59,"props":183,"children":184},{},[185,187,193,195,201],{"type":49,"value":186},"Then fetch specific pages with ",{"type":43,"tag":121,"props":188,"children":190},{"className":189},[],[191],{"type":49,"value":192},".md",{"type":49,"value":194}," suffix for markdown format (e.g., ",{"type":43,"tag":121,"props":196,"children":198},{"className":197},[],[199],{"type":49,"value":200},"https:\u002F\u002Fmodelcontextprotocol.io\u002Fspecification\u002Fdraft.md",{"type":49,"value":202},").",{"type":43,"tag":59,"props":204,"children":205},{},[206],{"type":49,"value":207},"Key pages to review:",{"type":43,"tag":209,"props":210,"children":211},"ul",{},[212,218,223],{"type":43,"tag":213,"props":214,"children":215},"li",{},[216],{"type":49,"value":217},"Specification overview and architecture",{"type":43,"tag":213,"props":219,"children":220},{},[221],{"type":49,"value":222},"Transport mechanisms (streamable HTTP, stdio)",{"type":43,"tag":213,"props":224,"children":225},{},[226],{"type":49,"value":227},"Tool, resource, and prompt definitions",{"type":43,"tag":93,"props":229,"children":231},{"id":230},"_13-study-framework-documentation",[232],{"type":49,"value":233},"1.3 Study Framework Documentation",{"type":43,"tag":59,"props":235,"children":236},{},[237],{"type":43,"tag":103,"props":238,"children":239},{},[240],{"type":49,"value":241},"Recommended stack:",{"type":43,"tag":209,"props":243,"children":244},{},[245,255],{"type":43,"tag":213,"props":246,"children":247},{},[248,253],{"type":43,"tag":103,"props":249,"children":250},{},[251],{"type":49,"value":252},"Language",{"type":49,"value":254},": TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)",{"type":43,"tag":213,"props":256,"children":257},{},[258,263],{"type":43,"tag":103,"props":259,"children":260},{},[261],{"type":49,"value":262},"Transport",{"type":49,"value":264},": Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.",{"type":43,"tag":59,"props":266,"children":267},{},[268],{"type":43,"tag":103,"props":269,"children":270},{},[271],{"type":49,"value":272},"Load framework documentation:",{"type":43,"tag":209,"props":274,"children":275},{},[276],{"type":43,"tag":213,"props":277,"children":278},{},[279,284,286,293],{"type":43,"tag":103,"props":280,"children":281},{},[282],{"type":49,"value":283},"MCP Best Practices",{"type":49,"value":285},": ",{"type":43,"tag":287,"props":288,"children":290},"a",{"href":289},".\u002Freference\u002Fmcp_best_practices.md",[291],{"type":49,"value":292},"📋 View Best Practices",{"type":49,"value":294}," - Core guidelines",{"type":43,"tag":59,"props":296,"children":297},{},[298],{"type":43,"tag":103,"props":299,"children":300},{},[301],{"type":49,"value":302},"For TypeScript (recommended):",{"type":43,"tag":209,"props":304,"children":305},{},[306,322],{"type":43,"tag":213,"props":307,"children":308},{},[309,314,316],{"type":43,"tag":103,"props":310,"children":311},{},[312],{"type":49,"value":313},"TypeScript SDK",{"type":49,"value":315},": Use WebFetch to load ",{"type":43,"tag":121,"props":317,"children":319},{"className":318},[],[320],{"type":49,"value":321},"https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\u002Fmain\u002FREADME.md",{"type":43,"tag":213,"props":323,"children":324},{},[325,331],{"type":43,"tag":287,"props":326,"children":328},{"href":327},".\u002Freference\u002Fnode_mcp_server.md",[329],{"type":49,"value":330},"⚡ TypeScript Guide",{"type":49,"value":332}," - TypeScript patterns and examples",{"type":43,"tag":59,"props":334,"children":335},{},[336],{"type":43,"tag":103,"props":337,"children":338},{},[339],{"type":49,"value":340},"For Python:",{"type":43,"tag":209,"props":342,"children":343},{},[344,359],{"type":43,"tag":213,"props":345,"children":346},{},[347,352,353],{"type":43,"tag":103,"props":348,"children":349},{},[350],{"type":49,"value":351},"Python SDK",{"type":49,"value":315},{"type":43,"tag":121,"props":354,"children":356},{"className":355},[],[357],{"type":49,"value":358},"https:\u002F\u002Fraw.githubusercontent.com\u002Fmodelcontextprotocol\u002Fpython-sdk\u002Fmain\u002FREADME.md",{"type":43,"tag":213,"props":360,"children":361},{},[362,368],{"type":43,"tag":287,"props":363,"children":365},{"href":364},".\u002Freference\u002Fpython_mcp_server.md",[366],{"type":49,"value":367},"🐍 Python Guide",{"type":49,"value":369}," - Python patterns and examples",{"type":43,"tag":93,"props":371,"children":373},{"id":372},"_14-plan-your-implementation",[374],{"type":49,"value":375},"1.4 Plan Your Implementation",{"type":43,"tag":59,"props":377,"children":378},{},[379,384],{"type":43,"tag":103,"props":380,"children":381},{},[382],{"type":49,"value":383},"Understand the API:",{"type":49,"value":385},"\nReview the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.",{"type":43,"tag":59,"props":387,"children":388},{},[389,394],{"type":43,"tag":103,"props":390,"children":391},{},[392],{"type":49,"value":393},"Tool Selection:",{"type":49,"value":395},"\nPrioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.",{"type":43,"tag":65,"props":397,"children":398},{},[],{"type":43,"tag":86,"props":400,"children":402},{"id":401},"phase-2-implementation",[403],{"type":49,"value":404},"Phase 2: Implementation",{"type":43,"tag":93,"props":406,"children":408},{"id":407},"_21-set-up-project-structure",[409],{"type":49,"value":410},"2.1 Set Up Project Structure",{"type":43,"tag":59,"props":412,"children":413},{},[414],{"type":49,"value":415},"See language-specific guides for project setup:",{"type":43,"tag":209,"props":417,"children":418},{},[419,428],{"type":43,"tag":213,"props":420,"children":421},{},[422,426],{"type":43,"tag":287,"props":423,"children":424},{"href":327},[425],{"type":49,"value":330},{"type":49,"value":427}," - Project structure, package.json, tsconfig.json",{"type":43,"tag":213,"props":429,"children":430},{},[431,435],{"type":43,"tag":287,"props":432,"children":433},{"href":364},[434],{"type":49,"value":367},{"type":49,"value":436}," - Module organization, dependencies",{"type":43,"tag":93,"props":438,"children":440},{"id":439},"_22-implement-core-infrastructure",[441],{"type":49,"value":442},"2.2 Implement Core Infrastructure",{"type":43,"tag":59,"props":444,"children":445},{},[446],{"type":49,"value":447},"Create shared utilities:",{"type":43,"tag":209,"props":449,"children":450},{},[451,456,461,466],{"type":43,"tag":213,"props":452,"children":453},{},[454],{"type":49,"value":455},"API client with authentication",{"type":43,"tag":213,"props":457,"children":458},{},[459],{"type":49,"value":460},"Error handling helpers",{"type":43,"tag":213,"props":462,"children":463},{},[464],{"type":49,"value":465},"Response formatting (JSON\u002FMarkdown)",{"type":43,"tag":213,"props":467,"children":468},{},[469],{"type":49,"value":470},"Pagination support",{"type":43,"tag":93,"props":472,"children":474},{"id":473},"_23-implement-tools",[475],{"type":49,"value":476},"2.3 Implement Tools",{"type":43,"tag":59,"props":478,"children":479},{},[480],{"type":49,"value":481},"For each tool:",{"type":43,"tag":59,"props":483,"children":484},{},[485],{"type":43,"tag":103,"props":486,"children":487},{},[488],{"type":49,"value":489},"Input Schema:",{"type":43,"tag":209,"props":491,"children":492},{},[493,498,503],{"type":43,"tag":213,"props":494,"children":495},{},[496],{"type":49,"value":497},"Use Zod (TypeScript) or Pydantic (Python)",{"type":43,"tag":213,"props":499,"children":500},{},[501],{"type":49,"value":502},"Include constraints and clear descriptions",{"type":43,"tag":213,"props":504,"children":505},{},[506],{"type":49,"value":507},"Add examples in field descriptions",{"type":43,"tag":59,"props":509,"children":510},{},[511],{"type":43,"tag":103,"props":512,"children":513},{},[514],{"type":49,"value":515},"Output Schema:",{"type":43,"tag":209,"props":517,"children":518},{},[519,532,545],{"type":43,"tag":213,"props":520,"children":521},{},[522,524,530],{"type":49,"value":523},"Define ",{"type":43,"tag":121,"props":525,"children":527},{"className":526},[],[528],{"type":49,"value":529},"outputSchema",{"type":49,"value":531}," where possible for structured data",{"type":43,"tag":213,"props":533,"children":534},{},[535,537,543],{"type":49,"value":536},"Use ",{"type":43,"tag":121,"props":538,"children":540},{"className":539},[],[541],{"type":49,"value":542},"structuredContent",{"type":49,"value":544}," in tool responses (TypeScript SDK feature)",{"type":43,"tag":213,"props":546,"children":547},{},[548],{"type":49,"value":549},"Helps clients understand and process tool outputs",{"type":43,"tag":59,"props":551,"children":552},{},[553],{"type":43,"tag":103,"props":554,"children":555},{},[556],{"type":49,"value":557},"Tool Description:",{"type":43,"tag":209,"props":559,"children":560},{},[561,566,571],{"type":43,"tag":213,"props":562,"children":563},{},[564],{"type":49,"value":565},"Concise summary of functionality",{"type":43,"tag":213,"props":567,"children":568},{},[569],{"type":49,"value":570},"Parameter descriptions",{"type":43,"tag":213,"props":572,"children":573},{},[574],{"type":49,"value":575},"Return type schema",{"type":43,"tag":59,"props":577,"children":578},{},[579],{"type":43,"tag":103,"props":580,"children":581},{},[582],{"type":49,"value":583},"Implementation:",{"type":43,"tag":209,"props":585,"children":586},{},[587,592,597,602],{"type":43,"tag":213,"props":588,"children":589},{},[590],{"type":49,"value":591},"Async\u002Fawait for I\u002FO operations",{"type":43,"tag":213,"props":593,"children":594},{},[595],{"type":49,"value":596},"Proper error handling with actionable messages",{"type":43,"tag":213,"props":598,"children":599},{},[600],{"type":49,"value":601},"Support pagination where applicable",{"type":43,"tag":213,"props":603,"children":604},{},[605],{"type":49,"value":606},"Return both text content and structured data when using modern SDKs",{"type":43,"tag":59,"props":608,"children":609},{},[610],{"type":43,"tag":103,"props":611,"children":612},{},[613],{"type":49,"value":614},"Annotations:",{"type":43,"tag":209,"props":616,"children":617},{},[618,629,639,649],{"type":43,"tag":213,"props":619,"children":620},{},[621,627],{"type":43,"tag":121,"props":622,"children":624},{"className":623},[],[625],{"type":49,"value":626},"readOnlyHint",{"type":49,"value":628},": true\u002Ffalse",{"type":43,"tag":213,"props":630,"children":631},{},[632,638],{"type":43,"tag":121,"props":633,"children":635},{"className":634},[],[636],{"type":49,"value":637},"destructiveHint",{"type":49,"value":628},{"type":43,"tag":213,"props":640,"children":641},{},[642,648],{"type":43,"tag":121,"props":643,"children":645},{"className":644},[],[646],{"type":49,"value":647},"idempotentHint",{"type":49,"value":628},{"type":43,"tag":213,"props":650,"children":651},{},[652,658],{"type":43,"tag":121,"props":653,"children":655},{"className":654},[],[656],{"type":49,"value":657},"openWorldHint",{"type":49,"value":628},{"type":43,"tag":65,"props":660,"children":661},{},[],{"type":43,"tag":86,"props":663,"children":665},{"id":664},"phase-3-review-and-test",[666],{"type":49,"value":667},"Phase 3: Review and Test",{"type":43,"tag":93,"props":669,"children":671},{"id":670},"_31-code-quality",[672],{"type":49,"value":673},"3.1 Code Quality",{"type":43,"tag":59,"props":675,"children":676},{},[677],{"type":49,"value":678},"Review for:",{"type":43,"tag":209,"props":680,"children":681},{},[682,687,692,697],{"type":43,"tag":213,"props":683,"children":684},{},[685],{"type":49,"value":686},"No duplicated code (DRY principle)",{"type":43,"tag":213,"props":688,"children":689},{},[690],{"type":49,"value":691},"Consistent error handling",{"type":43,"tag":213,"props":693,"children":694},{},[695],{"type":49,"value":696},"Full type coverage",{"type":43,"tag":213,"props":698,"children":699},{},[700],{"type":49,"value":701},"Clear tool descriptions",{"type":43,"tag":93,"props":703,"children":705},{"id":704},"_32-build-and-test",[706],{"type":49,"value":707},"3.2 Build and Test",{"type":43,"tag":59,"props":709,"children":710},{},[711],{"type":43,"tag":103,"props":712,"children":713},{},[714],{"type":49,"value":715},"TypeScript:",{"type":43,"tag":209,"props":717,"children":718},{},[719,732],{"type":43,"tag":213,"props":720,"children":721},{},[722,724,730],{"type":49,"value":723},"Run ",{"type":43,"tag":121,"props":725,"children":727},{"className":726},[],[728],{"type":49,"value":729},"npm run build",{"type":49,"value":731}," to verify compilation",{"type":43,"tag":213,"props":733,"children":734},{},[735,737],{"type":49,"value":736},"Test with MCP Inspector: ",{"type":43,"tag":121,"props":738,"children":740},{"className":739},[],[741],{"type":49,"value":742},"npx @modelcontextprotocol\u002Finspector",{"type":43,"tag":59,"props":744,"children":745},{},[746],{"type":43,"tag":103,"props":747,"children":748},{},[749],{"type":49,"value":750},"Python:",{"type":43,"tag":209,"props":752,"children":753},{},[754,765],{"type":43,"tag":213,"props":755,"children":756},{},[757,759],{"type":49,"value":758},"Verify syntax: ",{"type":43,"tag":121,"props":760,"children":762},{"className":761},[],[763],{"type":49,"value":764},"python -m py_compile your_server.py",{"type":43,"tag":213,"props":766,"children":767},{},[768],{"type":49,"value":769},"Test with MCP Inspector",{"type":43,"tag":59,"props":771,"children":772},{},[773],{"type":49,"value":774},"See language-specific guides for detailed testing approaches and quality checklists.",{"type":43,"tag":65,"props":776,"children":777},{},[],{"type":43,"tag":86,"props":779,"children":781},{"id":780},"phase-4-create-evaluations",[782],{"type":49,"value":783},"Phase 4: Create Evaluations",{"type":43,"tag":59,"props":785,"children":786},{},[787],{"type":49,"value":788},"After implementing your MCP server, create comprehensive evaluations to test its effectiveness.",{"type":43,"tag":59,"props":790,"children":791},{},[792],{"type":43,"tag":103,"props":793,"children":794},{},[795,797,803],{"type":49,"value":796},"Load ",{"type":43,"tag":287,"props":798,"children":800},{"href":799},".\u002Freference\u002Fevaluation.md",[801],{"type":49,"value":802},"✅ Evaluation Guide",{"type":49,"value":804}," for complete evaluation guidelines.",{"type":43,"tag":93,"props":806,"children":808},{"id":807},"_41-understand-evaluation-purpose",[809],{"type":49,"value":810},"4.1 Understand Evaluation Purpose",{"type":43,"tag":59,"props":812,"children":813},{},[814],{"type":49,"value":815},"Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.",{"type":43,"tag":93,"props":817,"children":819},{"id":818},"_42-create-10-evaluation-questions",[820],{"type":49,"value":821},"4.2 Create 10 Evaluation Questions",{"type":43,"tag":59,"props":823,"children":824},{},[825],{"type":49,"value":826},"To create effective evaluations, follow the process outlined in the evaluation guide:",{"type":43,"tag":828,"props":829,"children":830},"ol",{},[831,841,851,861],{"type":43,"tag":213,"props":832,"children":833},{},[834,839],{"type":43,"tag":103,"props":835,"children":836},{},[837],{"type":49,"value":838},"Tool Inspection",{"type":49,"value":840},": List available tools and understand their capabilities",{"type":43,"tag":213,"props":842,"children":843},{},[844,849],{"type":43,"tag":103,"props":845,"children":846},{},[847],{"type":49,"value":848},"Content Exploration",{"type":49,"value":850},": Use READ-ONLY operations to explore available data",{"type":43,"tag":213,"props":852,"children":853},{},[854,859],{"type":43,"tag":103,"props":855,"children":856},{},[857],{"type":49,"value":858},"Question Generation",{"type":49,"value":860},": Create 10 complex, realistic questions",{"type":43,"tag":213,"props":862,"children":863},{},[864,869],{"type":43,"tag":103,"props":865,"children":866},{},[867],{"type":49,"value":868},"Answer Verification",{"type":49,"value":870},": Solve each question yourself to verify answers",{"type":43,"tag":93,"props":872,"children":874},{"id":873},"_43-evaluation-requirements",[875],{"type":49,"value":876},"4.3 Evaluation Requirements",{"type":43,"tag":59,"props":878,"children":879},{},[880],{"type":49,"value":881},"Ensure each question is:",{"type":43,"tag":209,"props":883,"children":884},{},[885,895,905,915,925,935],{"type":43,"tag":213,"props":886,"children":887},{},[888,893],{"type":43,"tag":103,"props":889,"children":890},{},[891],{"type":49,"value":892},"Independent",{"type":49,"value":894},": Not dependent on other questions",{"type":43,"tag":213,"props":896,"children":897},{},[898,903],{"type":43,"tag":103,"props":899,"children":900},{},[901],{"type":49,"value":902},"Read-only",{"type":49,"value":904},": Only non-destructive operations required",{"type":43,"tag":213,"props":906,"children":907},{},[908,913],{"type":43,"tag":103,"props":909,"children":910},{},[911],{"type":49,"value":912},"Complex",{"type":49,"value":914},": Requiring multiple tool calls and deep exploration",{"type":43,"tag":213,"props":916,"children":917},{},[918,923],{"type":43,"tag":103,"props":919,"children":920},{},[921],{"type":49,"value":922},"Realistic",{"type":49,"value":924},": Based on real use cases humans would care about",{"type":43,"tag":213,"props":926,"children":927},{},[928,933],{"type":43,"tag":103,"props":929,"children":930},{},[931],{"type":49,"value":932},"Verifiable",{"type":49,"value":934},": Single, clear answer that can be verified by string comparison",{"type":43,"tag":213,"props":936,"children":937},{},[938,943],{"type":43,"tag":103,"props":939,"children":940},{},[941],{"type":49,"value":942},"Stable",{"type":49,"value":944},": Answer won't change over time",{"type":43,"tag":93,"props":946,"children":948},{"id":947},"_44-output-format",[949],{"type":49,"value":950},"4.4 Output Format",{"type":43,"tag":59,"props":952,"children":953},{},[954],{"type":49,"value":955},"Create an XML file with this structure:",{"type":43,"tag":957,"props":958,"children":963},"pre",{"className":959,"code":960,"language":961,"meta":962,"style":962},"language-xml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\u003Cevaluation>\n  \u003Cqa_pair>\n    \u003Cquestion>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?\u003C\u002Fquestion>\n    \u003Canswer>3\u003C\u002Fanswer>\n  \u003C\u002Fqa_pair>\n\u003C!-- More qa_pairs... -->\n\u003C\u002Fevaluation>\n","xml","",[964],{"type":43,"tag":121,"props":965,"children":966},{"__ignoreMap":962},[967,978,987,996,1005,1014,1023],{"type":43,"tag":968,"props":969,"children":972},"span",{"class":970,"line":971},"line",1,[973],{"type":43,"tag":968,"props":974,"children":975},{},[976],{"type":49,"value":977},"\u003Cevaluation>\n",{"type":43,"tag":968,"props":979,"children":981},{"class":970,"line":980},2,[982],{"type":43,"tag":968,"props":983,"children":984},{},[985],{"type":49,"value":986},"  \u003Cqa_pair>\n",{"type":43,"tag":968,"props":988,"children":990},{"class":970,"line":989},3,[991],{"type":43,"tag":968,"props":992,"children":993},{},[994],{"type":49,"value":995},"    \u003Cquestion>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?\u003C\u002Fquestion>\n",{"type":43,"tag":968,"props":997,"children":999},{"class":970,"line":998},4,[1000],{"type":43,"tag":968,"props":1001,"children":1002},{},[1003],{"type":49,"value":1004},"    \u003Canswer>3\u003C\u002Fanswer>\n",{"type":43,"tag":968,"props":1006,"children":1008},{"class":970,"line":1007},5,[1009],{"type":43,"tag":968,"props":1010,"children":1011},{},[1012],{"type":49,"value":1013},"  \u003C\u002Fqa_pair>\n",{"type":43,"tag":968,"props":1015,"children":1017},{"class":970,"line":1016},6,[1018],{"type":43,"tag":968,"props":1019,"children":1020},{},[1021],{"type":49,"value":1022},"\u003C!-- More qa_pairs... -->\n",{"type":43,"tag":968,"props":1024,"children":1026},{"class":970,"line":1025},7,[1027],{"type":43,"tag":968,"props":1028,"children":1029},{},[1030],{"type":49,"value":1031},"\u003C\u002Fevaluation>\n",{"type":43,"tag":65,"props":1033,"children":1034},{},[],{"type":43,"tag":44,"props":1036,"children":1038},{"id":1037},"reference-files",[1039],{"type":49,"value":1040},"Reference Files",{"type":43,"tag":52,"props":1042,"children":1044},{"id":1043},"documentation-library",[1045],{"type":49,"value":1046},"📚 Documentation Library",{"type":43,"tag":59,"props":1048,"children":1049},{},[1050],{"type":49,"value":1051},"Load these resources as needed during development:",{"type":43,"tag":86,"props":1053,"children":1055},{"id":1054},"core-mcp-documentation-load-first",[1056],{"type":49,"value":1057},"Core MCP Documentation (Load First)",{"type":43,"tag":209,"props":1059,"children":1060},{},[1061,1085],{"type":43,"tag":213,"props":1062,"children":1063},{},[1064,1069,1071,1076,1078,1083],{"type":43,"tag":103,"props":1065,"children":1066},{},[1067],{"type":49,"value":1068},"MCP Protocol",{"type":49,"value":1070},": Start with sitemap at ",{"type":43,"tag":121,"props":1072,"children":1074},{"className":1073},[],[1075],{"type":49,"value":181},{"type":49,"value":1077},", then fetch specific pages with ",{"type":43,"tag":121,"props":1079,"children":1081},{"className":1080},[],[1082],{"type":49,"value":192},{"type":49,"value":1084}," suffix",{"type":43,"tag":213,"props":1086,"children":1087},{},[1088,1093,1095],{"type":43,"tag":287,"props":1089,"children":1090},{"href":289},[1091],{"type":49,"value":1092},"📋 MCP Best Practices",{"type":49,"value":1094}," - Universal MCP guidelines including:\n",{"type":43,"tag":209,"props":1096,"children":1097},{},[1098,1103,1108,1113,1118],{"type":43,"tag":213,"props":1099,"children":1100},{},[1101],{"type":49,"value":1102},"Server and tool naming conventions",{"type":43,"tag":213,"props":1104,"children":1105},{},[1106],{"type":49,"value":1107},"Response format guidelines (JSON vs Markdown)",{"type":43,"tag":213,"props":1109,"children":1110},{},[1111],{"type":49,"value":1112},"Pagination best practices",{"type":43,"tag":213,"props":1114,"children":1115},{},[1116],{"type":49,"value":1117},"Transport selection (streamable HTTP vs stdio)",{"type":43,"tag":213,"props":1119,"children":1120},{},[1121],{"type":49,"value":1122},"Security and error handling standards",{"type":43,"tag":86,"props":1124,"children":1126},{"id":1125},"sdk-documentation-load-during-phase-12",[1127],{"type":49,"value":1128},"SDK Documentation (Load During Phase 1\u002F2)",{"type":43,"tag":209,"props":1130,"children":1131},{},[1132,1146],{"type":43,"tag":213,"props":1133,"children":1134},{},[1135,1139,1141],{"type":43,"tag":103,"props":1136,"children":1137},{},[1138],{"type":49,"value":351},{"type":49,"value":1140},": Fetch from ",{"type":43,"tag":121,"props":1142,"children":1144},{"className":1143},[],[1145],{"type":49,"value":358},{"type":43,"tag":213,"props":1147,"children":1148},{},[1149,1153,1154],{"type":43,"tag":103,"props":1150,"children":1151},{},[1152],{"type":49,"value":313},{"type":49,"value":1140},{"type":43,"tag":121,"props":1155,"children":1157},{"className":1156},[],[1158],{"type":49,"value":321},{"type":43,"tag":86,"props":1160,"children":1162},{"id":1161},"language-specific-implementation-guides-load-during-phase-2",[1163],{"type":49,"value":1164},"Language-Specific Implementation Guides (Load During Phase 2)",{"type":43,"tag":209,"props":1166,"children":1167},{},[1168,1212],{"type":43,"tag":213,"props":1169,"children":1170},{},[1171,1176,1178],{"type":43,"tag":287,"props":1172,"children":1173},{"href":364},[1174],{"type":49,"value":1175},"🐍 Python Implementation Guide",{"type":49,"value":1177}," - Complete Python\u002FFastMCP guide with:",{"type":43,"tag":209,"props":1179,"children":1180},{},[1181,1186,1191,1202,1207],{"type":43,"tag":213,"props":1182,"children":1183},{},[1184],{"type":49,"value":1185},"Server initialization patterns",{"type":43,"tag":213,"props":1187,"children":1188},{},[1189],{"type":49,"value":1190},"Pydantic model examples",{"type":43,"tag":213,"props":1192,"children":1193},{},[1194,1196],{"type":49,"value":1195},"Tool registration with ",{"type":43,"tag":121,"props":1197,"children":1199},{"className":1198},[],[1200],{"type":49,"value":1201},"@mcp.tool",{"type":43,"tag":213,"props":1203,"children":1204},{},[1205],{"type":49,"value":1206},"Complete working examples",{"type":43,"tag":213,"props":1208,"children":1209},{},[1210],{"type":49,"value":1211},"Quality checklist",{"type":43,"tag":213,"props":1213,"children":1214},{},[1215,1220,1222],{"type":43,"tag":287,"props":1216,"children":1217},{"href":327},[1218],{"type":49,"value":1219},"⚡ TypeScript Implementation Guide",{"type":49,"value":1221}," - Complete TypeScript guide with:",{"type":43,"tag":209,"props":1223,"children":1224},{},[1225,1230,1235,1245,1249],{"type":43,"tag":213,"props":1226,"children":1227},{},[1228],{"type":49,"value":1229},"Project structure",{"type":43,"tag":213,"props":1231,"children":1232},{},[1233],{"type":49,"value":1234},"Zod schema patterns",{"type":43,"tag":213,"props":1236,"children":1237},{},[1238,1239],{"type":49,"value":1195},{"type":43,"tag":121,"props":1240,"children":1242},{"className":1241},[],[1243],{"type":49,"value":1244},"server.registerTool",{"type":43,"tag":213,"props":1246,"children":1247},{},[1248],{"type":49,"value":1206},{"type":43,"tag":213,"props":1250,"children":1251},{},[1252],{"type":49,"value":1211},{"type":43,"tag":86,"props":1254,"children":1256},{"id":1255},"evaluation-guide-load-during-phase-4",[1257],{"type":49,"value":1258},"Evaluation Guide (Load During Phase 4)",{"type":43,"tag":209,"props":1260,"children":1261},{},[1262],{"type":43,"tag":213,"props":1263,"children":1264},{},[1265,1269,1271],{"type":43,"tag":287,"props":1266,"children":1267},{"href":799},[1268],{"type":49,"value":802},{"type":49,"value":1270}," - Complete evaluation creation guide with:\n",{"type":43,"tag":209,"props":1272,"children":1273},{},[1274,1279,1284,1289,1294],{"type":43,"tag":213,"props":1275,"children":1276},{},[1277],{"type":49,"value":1278},"Question creation guidelines",{"type":43,"tag":213,"props":1280,"children":1281},{},[1282],{"type":49,"value":1283},"Answer verification strategies",{"type":43,"tag":213,"props":1285,"children":1286},{},[1287],{"type":49,"value":1288},"XML format specifications",{"type":43,"tag":213,"props":1290,"children":1291},{},[1292],{"type":49,"value":1293},"Example questions and answers",{"type":43,"tag":213,"props":1295,"children":1296},{},[1297],{"type":49,"value":1298},"Running an evaluation with the provided scripts",{"type":43,"tag":1300,"props":1301,"children":1302},"style",{},[1303],{"type":49,"value":1304},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1306,"total":1428},[1307,1326,1341,1357,1372,1395,1412],{"slug":1308,"name":1308,"fn":1309,"description":1310,"org":1311,"tags":1312,"stars":22,"repoUrl":23,"updatedAt":1325},"algorithmic-art","create generative art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1313,1316,1319,1322],{"name":1314,"slug":1315,"type":15},"Creative","creative",{"name":1317,"slug":1318,"type":15},"Generative Art","generative-art",{"name":1320,"slug":1321,"type":15},"Graphics","graphics",{"name":1323,"slug":1324,"type":15},"JavaScript","javascript","2026-07-13T06:41:35.540127",{"slug":1327,"name":1327,"fn":1328,"description":1329,"org":1330,"tags":1331,"stars":22,"repoUrl":23,"updatedAt":1340},"antfu","configure JavaScript projects with Anthony Fu's tools","Anthony Fu's opinionated tooling and conventions for JavaScript\u002FTypeScript projects. Use when setting up new projects, configuring ESLint\u002FPrettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1332,1335,1336,1337],{"name":1333,"slug":1334,"type":15},"Best Practices","best-practices",{"name":17,"slug":18,"type":15},{"name":1323,"slug":1324,"type":15},{"name":1338,"slug":1339,"type":15},"TypeScript","typescript","2026-07-13T06:43:13.153309",{"slug":1342,"name":1342,"fn":1343,"description":1344,"org":1345,"tags":1346,"stars":22,"repoUrl":23,"updatedAt":1356},"brand-guidelines","apply Anthropic brand guidelines","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1347,1350,1353],{"name":1348,"slug":1349,"type":15},"Branding","branding",{"name":1351,"slug":1352,"type":15},"Design","design",{"name":1354,"slug":1355,"type":15},"Typography","typography","2026-07-13T06:43:06.077629",{"slug":1358,"name":1358,"fn":1359,"description":1360,"org":1361,"tags":1362,"stars":22,"repoUrl":23,"updatedAt":1371},"canvas-design","create visual art and design assets","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1363,1364,1365,1368],{"name":1314,"slug":1315,"type":15},{"name":1351,"slug":1352,"type":15},{"name":1366,"slug":1367,"type":15},"Images","images",{"name":1369,"slug":1370,"type":15},"PDF","pdf","2026-07-13T06:39:58.803113",{"slug":1373,"name":1373,"fn":1374,"description":1375,"org":1376,"tags":1377,"stars":22,"repoUrl":23,"updatedAt":1394},"ci-cd-containerization-advisor","design CI\u002FCD pipelines for Kotlin applications","Design reproducible build, image, and deployment pipelines for Kotlin plus Spring applications, including CI verification, layered containers, rollout safety, and deployment-time migration coordination. Use when creating or improving Dockerfiles, CI workflows, image hardening, Kubernetes manifests, release gates, or deployment strategies for Spring Boot services, especially where build reproducibility and operational safety matter.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1378,1381,1384,1387,1388,1391],{"name":1379,"slug":1380,"type":15},"CI\u002FCD","ci-cd",{"name":1382,"slug":1383,"type":15},"Containers","containers",{"name":1385,"slug":1386,"type":15},"Deployment","deployment",{"name":17,"slug":18,"type":15},{"name":1389,"slug":1390,"type":15},"Kotlin","kotlin",{"name":1392,"slug":1393,"type":15},"Spring","spring","2026-07-13T06:41:47.83899",{"slug":1396,"name":1396,"fn":1397,"description":1398,"org":1399,"tags":1400,"stars":22,"repoUrl":23,"updatedAt":1411},"cloudflare-deploy","deploy applications to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1401,1404,1407,1410],{"name":1402,"slug":1403,"type":15},"Cloudflare","cloudflare",{"name":1405,"slug":1406,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1408,"slug":1409,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1385,"slug":1386,"type":15},"2026-07-17T06:04:42.853896",{"slug":1413,"name":1413,"fn":1414,"description":1415,"org":1416,"tags":1417,"stars":22,"repoUrl":23,"updatedAt":1427},"compose-ui-control","interact with Compose Desktop applications","Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1418,1421,1424],{"name":1419,"slug":1420,"type":15},"Automation","automation",{"name":1422,"slug":1423,"type":15},"Desktop","desktop",{"name":1425,"slug":1426,"type":15},"UI Components","ui-components","2026-07-13T06:40:38.798626",128,{"items":1430,"total":1555},[1431,1447,1456,1465,1476,1486,1495,1504,1513,1523,1532,1545],{"slug":1432,"name":1432,"fn":1433,"description":1434,"org":1435,"tags":1436,"stars":1444,"repoUrl":1445,"updatedAt":1446},"mps-aspect-accessories","configure JetBrains MPS module dependencies","Wire MPS module and model dependencies, used languages, used devkits, extended languages, runtime solutions, accessory models, and language\u002Fdependency versions. Use when adding\u002Fremoving module dependencies, importing languages or devkits into a model, declaring runtime solutions, or shipping accessory content visible to consumers without explicit import.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1437,1440,1443],{"name":1438,"slug":1439,"type":15},"Architecture","architecture",{"name":1441,"slug":1442,"type":15},"Configuration","configuration",{"name":17,"slug":18,"type":15},1650,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002FMPS","2026-07-17T06:06:57.311661",{"slug":1448,"name":1448,"fn":1449,"description":1450,"org":1451,"tags":1452,"stars":1444,"repoUrl":1445,"updatedAt":1455},"mps-aspect-actions","define and edit MPS node factories","Use when defining or editing MPS node factories (the \"actions\" aspect) — `NodeFactories` roots, per-concept `NodeFactory` setup functions that initialize a freshly created node and optionally copy data from a replaced `sampleNode`, plus the actions aspect's `CopyPasteHandlers` and `PasteWrappers` roots. Reach for this skill when a substitution, side transform, completion replacement, or `add new initialized(...)` should preserve fields from the node it is replacing, or when defaults set in a constructor are not enough.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1453,1454],{"name":1438,"slug":1439,"type":15},{"name":17,"slug":18,"type":15},"2026-07-17T06:04:48.066901",{"slug":1457,"name":1457,"fn":1458,"description":1459,"org":1460,"tags":1461,"stars":1444,"repoUrl":1445,"updatedAt":1464},"mps-aspect-behavior","define and edit MPS concept behavior","Use when defining or editing MPS `ConceptBehavior` — per-concept methods (non-virtual \u002F virtual \u002F abstract \u002F static \u002F virtual static), constructors, virtual dispatch (MRO), super and interface-default calls (`super\u003CInterface>.method`), overriding methods from `lang.core.behavior` interfaces such as `ScopeProvider.getScope` \u002F `INamedConcept.getName` \u002F `BaseConcept.getPresentation`, calling sibling methods (`LocalBehaviorMethodCall`) and behavior methods from other aspects via `node.method(...)`. Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fbehavior.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1462,1463],{"name":1438,"slug":1439,"type":15},{"name":17,"slug":18,"type":15},"2026-07-13T06:45:21.757084",{"slug":1466,"name":1466,"fn":1467,"description":1468,"org":1469,"tags":1470,"stars":1444,"repoUrl":1445,"updatedAt":1475},"mps-aspect-constraints","define JetBrains MPS language constraints","Use when defining or editing MPS language constraints — property validators \u002F setters \u002F getters, referent search scopes (imperative or inherited via `ScopeProvider.getScope`), `referentSetHandler` side effects, default-scope blocks, `canBeChild` \u002F `canBeParent` \u002F `canBeAncestor` \u002F `canBeRoot` placement rules, `defaultConcreteConcept` for abstract concepts, `set \u003Cread-only>` and `{name}` aliasing, and scope helpers (`SimpleRoleScope`, `ListScope`, `CompositeScope`, `HidingByNameScope`). Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fconstraints.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1471,1472],{"name":1438,"slug":1439,"type":15},{"name":1473,"slug":1474,"type":15},"Code Analysis","code-analysis","2026-07-23T05:41:33.639365",{"slug":1477,"name":1477,"fn":1478,"description":1479,"org":1480,"tags":1481,"stars":1444,"repoUrl":1445,"updatedAt":1485},"mps-aspect-dataflow","define and debug MPS dataflow builders","Use when defining or debugging MPS dataflow builders for a concept — control\u002Fdata flow declarations that drive reachability analysis and variable-use checking. Covers DataFlowBuilderDeclaration, BuilderBlock, emit instructions (code for, jump, ifjump, label, read, write, ret, mayBeUnreachable), positions (AfterPosition, BeforePosition, LabelPosition), the jetbrains.mps.lang.dataFlow language, the NodeParameter implicit, BL+smodel usage inside builder bodies, and IBuilderMode for advanced analyses such as nullable\u002Fnon-null tracking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1482],{"name":1483,"slug":1484,"type":15},"Data Analysis","data-analysis","2026-07-13T06:45:19.114674",{"slug":1487,"name":1487,"fn":1488,"description":1489,"org":1490,"tags":1491,"stars":1444,"repoUrl":1445,"updatedAt":1494},"mps-aspect-editor","define MPS editor layouts","Use when creating or changing MPS editor definitions — the overall workflow from scaffolding a `ConceptEditorDeclaration` through componentizing reusable `EditorComponentDeclaration`s, refining cell models and cell layouts, applying style sheets and indent-layout style items, wiring smart references, leveraging inheritance via super-concepts and interfaces, inspecting (`print_node_json`, `show_node_representation`) and validating (`check_root_node_problems`). Covers `jetbrains.mps.lang.editor` cell models (`CellModel_RefNode`\u002F`CellModel_RefNodeList`\u002F`CellModel_RefCell`\u002F`CellModel_Property`\u002F`CellModel_Constant`), layout choices, and JSON blueprints for common editor shapes. For the non-layout side (action maps, keymaps, transformation\u002Fsubstitute menus) use `mps-aspect-editor-menus-and-keymaps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1492,1493],{"name":1351,"slug":1352,"type":15},{"name":1425,"slug":1426,"type":15},"2026-07-23T05:41:56.638151",{"slug":1496,"name":1496,"fn":1497,"description":1498,"org":1499,"tags":1500,"stars":1444,"repoUrl":1445,"updatedAt":1503},"mps-aspect-editor-menus-and-keymaps","author MPS editor menus and keymaps","Use when authoring the **non-layout** parts of the MPS editor aspect — what happens when the user types, presses a key, triggers completion, pastes, or invokes a context action. Covers action maps (`CellActionMapDeclaration`), cell keymaps (`CellKeyMapDeclaration`), transformation menus (`TransformationMenu_Default` \u002F `_Named` \u002F `_Contribution`), substitute menus (`SubstituteMenu_Default` \u002F `SubstituteMenu` \u002F contributions), side transforms (LEFT\u002FRIGHT), legacy cell menus, paste wrappers and copy-paste handlers (in the actions language), completion styling, reference presentation, two-step deletion, and the editor selection API. Trigger terms: `actionMap`, `keyMap`, `delete_action_id`, `transformationMenu`, `substituteMenu`, `Ctrl+Space`, `Ctrl+Alt+B`, side transform, paste wrapper, completion styling, `PasteWrappers`, `CopyPasteHandlers`. For the **layout** side (cells, layouts, style sheets) use `mps-aspect-editor` instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1501,1502],{"name":17,"slug":18,"type":15},{"name":1425,"slug":1426,"type":15},"2026-07-23T05:41:49.666535",{"slug":1505,"name":1505,"fn":1506,"description":1507,"org":1508,"tags":1509,"stars":1444,"repoUrl":1445,"updatedAt":1512},"mps-aspect-generation-plan","modify MPS generation plans","Use when defining or modifying an MPS generation plan — explicit ordering of generators, checkpoints for cross-model reference resolution, forks for parallel branches, IncludePlan composition, conditional PlanContribution activation, ParameterEquals\u002FConceptListSelector fork selectors, and InitModelAttributes for targetFacet routing. Apply when working with @genplan models, the jetbrains.mps.lang.generator.plan language, attaching plans via DevKits or the Custom generation facet, or debugging cross-model mapping label resolution.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1510,1511],{"name":1438,"slug":1439,"type":15},{"name":17,"slug":18,"type":15},"2026-07-13T06:44:59.507855",{"slug":1514,"name":1514,"fn":1515,"description":1516,"org":1517,"tags":1518,"stars":1444,"repoUrl":1445,"updatedAt":1522},"mps-aspect-generator","define JetBrains MPS generator rules","Use when defining or modifying MPS generators — author a generator module, add or edit root\u002Freduction\u002Fweaving\u002Fpattern mapping rules, attach template macros ($COPY_SRC, $LOOP, $IF, $PROPERTY, $REF, $SWITCH, $MAP_SRC, $WEAVE, $INSERT, $LABEL, $TRACE, $VAR), wire mapping labels, build template switches, write pre\u002Fpost mapping scripts, navigate `genContext`, or debug \"rule didn't fire\", missing references, empty output, infinite reduction loops, and generated-Java compile failures.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1519,1520,1521],{"name":1438,"slug":1439,"type":15},{"name":1473,"slug":1474,"type":15},{"name":17,"slug":18,"type":15},"2026-07-17T06:06:58.042999",{"slug":1524,"name":1524,"fn":1525,"description":1526,"org":1527,"tags":1528,"stars":1444,"repoUrl":1445,"updatedAt":1531},"mps-aspect-intentions","define and edit MPS intentions","Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding `IntentionDeclaration` roots, parameterized or surround-with variants, description\u002FisApplicable\u002Fexecute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the language's `intentions` model and uses `jetbrains.mps.lang.intentions`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1529,1530],{"name":1438,"slug":1439,"type":15},{"name":17,"slug":18,"type":15},"2026-07-23T05:41:48.692899",{"slug":1533,"name":1533,"fn":1534,"description":1535,"org":1536,"tags":1537,"stars":1444,"repoUrl":1445,"updatedAt":1544},"mps-aspect-migrations","author and debug MPS migration scripts","Use when authoring or debugging MPS migration scripts that upgrade user models after a language definition changes — covers jetbrains.mps.lang.migration (MigrationScript class-based, PureMigrationScript declarative, MoveConcept\u002FMoveContainmentLink\u002FMoveReferenceLink\u002FMoveProperty, ordering via OrderDependency, data exchange via putData\u002FgetData, RefactoringLog, ConceptMigrationReference) and jetbrains.mps.lang.script Enhancement Scripts (MigrationScript with MigrationScriptPart_Instance, ExtractInterfaceMigration, FactoryMigrationScriptPart, CommentMigrationScriptPart) — when a model needs version-gated upgrade, concept rename or removal, link or property rename, instance-level transformation, or composition of migration steps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1538,1541],{"name":1539,"slug":1540,"type":15},"Debugging","debugging",{"name":1542,"slug":1543,"type":15},"Migration","migration","2026-07-13T06:45:20.372122",{"slug":1546,"name":1546,"fn":1547,"description":1548,"org":1549,"tags":1550,"stars":1444,"repoUrl":1445,"updatedAt":1554},"mps-aspect-structure-concepts","define concepts in MPS structure aspect","Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's `structure` aspect. Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation, and the full `mps_mcp_alter_structure` \u002F `mps_mcp_query_structure` reference. Use when authoring or modifying a language's structure model.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1551],{"name":1552,"slug":1553,"type":15},"Data Modeling","data-modeling","2026-07-23T05:41:30.705975",188]