[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AP46N00822H4B738BRMP7":3,"skill-same:01M79AP46N00822H4B738BRMP7":154},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":69,"commitSha":70,"skillDirectory":71,"forksCount":14,"repositoryHtmlUrl":72,"repositoryHomepageUrl":6,"ownerHtmlUrl":73,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":74,"install":75,"resources":87},"01M79AP46N00822H4B738BRMP7","typescript-mcp",null,"MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol\u002Fsdk. Use for API integrations, stateless tools, edge deployments, or encountering export syntax, schema validation, memory leak, CORS, auth errors.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"MIT","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: typescript-mcp\ndescription: \"MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol\u002Fsdk. Use for API integrations, stateless tools, edge deployments, or encountering export syntax, schema validation, memory leak, CORS, auth errors.\"\nlicense: MIT\nmetadata:\n  version: 2.0.0\n  last_updated: 2025-12-17\n  optimization_date: 2025-12-17\n  token_savings: ~55%\n  sdk_version: \"@modelcontextprotocol\u002Fsdk@1.22.0\"\n  platform: cloudflare-workers\n  production_tested: true\n  errors_prevented: 13\n  keywords:\n    - mcp\n    - model context protocol\n    - typescript mcp\n    - cloudflare workers mcp\n    - mcp server\n    - mcp tools\n    - mcp resources\n    - mcp sdk\n    - \"@modelcontextprotocol\u002Fsdk\"\n    - hono mcp\n    - streamablehttpservertransport\n    - mcp authentication\n    - mcp cloudflare\n    - edge mcp server\n    - serverless mcp\n    - typescript mcp server\n    - mcp api\n    - llm tools\n    - ai tools\n    - cloudflare d1 mcp\n    - cloudflare kv mcp\n    - mcp testing\n    - mcp deployment\n    - wrangler mcp\n    - export syntax error\n    - schema validation error\n    - memory leak mcp\n    - cors mcp\n    - rate limiting mcp\nallowed-tools: [Read, Write, Edit, Bash, Grep, Glob]\n---\n# TypeScript MCP Server on Cloudflare Workers\n\nBuild production-ready Model Context Protocol (MCP) servers using TypeScript and deploy them on Cloudflare Workers. This skill covers the official `@modelcontextprotocol\u002Fsdk`, HTTP transport setup, authentication patterns, Cloudflare service integrations, and comprehensive error prevention.\n\n---\n\n## When to Use This Skill\n\nUse this skill when:\n- Building **MCP servers** to expose APIs, tools, or data to LLMs\n- Deploying **serverless MCP endpoints** on Cloudflare Workers\n- Integrating **external APIs** as MCP tools (REST, GraphQL, databases)\n- Creating **stateless MCP servers** for edge deployment\n- Exposing **Cloudflare services** (D1, KV, R2, Vectorize) via MCP protocol\n- Implementing **authenticated MCP servers** with API keys, OAuth, or Zero Trust\n- Building **multi-tool MCP servers** with resources and prompts\n- Needing **production-ready templates** that prevent common MCP errors\n\n**Do NOT use this skill when**:\n- Building **Python MCP servers** (use FastMCP skill instead)\n- Needing **stateful agents** with WebSockets (use Cloudflare Agents SDK)\n- Wanting **long-running persistent agents** with SQLite storage (use Durable Objects)\n- Building **local CLI tools** (use stdio transport, not HTTP)\n\n---\n\n## Secure Installation\n\nMCP server packages grant tool access to LLMs — a compromised SDK can expose full system control. Verify packages before installing. Follow supply chain security best practices:\n\n- **Block post-install scripts** — `npm config set ignore-scripts true` (or Bun: disabled by default)\n- **Cooldown period** — Wait 7 days for new package versions to be vetted by the community\n- **Audit before installing** — Run `socket package score npm \u003Cpkg>` or use `socket npm install \u003Cpkg>` to check packages\n\nLoad the `dependency-upgrade` skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.\n\n## Core Concepts\n\n**MCP Protocol Components**:\n\n1. **Tools** - Functions LLMs can invoke (Zod schemas, async handlers, external APIs)\n2. **Resources** - Data exposure (URI-based: `config:\u002F\u002Fapp`, `user:\u002F\u002F{userId}`)\n3. **Prompts** - Pre-configured templates for LLM interactions\n4. **Completions** - Argument auto-complete (optional)\n\n---\n\n## Quick Start\n\n### 1. Install Dependencies\n\n```bash\nbun add @modelcontextprotocol\u002Fsdk hono zod\nbun add -d @cloudflare\u002Fworkers-types wrangler typescript\n```\n\n### 2. Create Basic MCP Server\n\n```typescript\nimport { McpServer } from '@modelcontextprotocol\u002Fsdk\u002Fserver\u002Fmcp.js';\nimport { StreamableHTTPServerTransport } from '@modelcontextprotocol\u002Fsdk\u002Fserver\u002FstreamableHttp.js';\nimport { Hono } from 'hono';\nimport { z } from 'zod';\n\nconst server = new McpServer({ name: 'my-mcp-server', version: '1.0.0' });\n\n\u002F\u002F Register a tool\nserver.registerTool(\n  'echo',\n  {\n    description: 'Echoes back the input text',\n    inputSchema: z.object({ text: z.string().describe('Text to echo') })\n  },\n  async ({ text }) => ({ content: [{ type: 'text', text }] })\n);\n\n\u002F\u002F HTTP endpoint\nconst app = new Hono();\n\napp.post('\u002Fmcp', async (c) => {\n  const transport = new StreamableHTTPServerTransport({\n    sessionIdGenerator: undefined,\n    enableJsonResponse: true\n  });\n\n  \u002F\u002F CRITICAL: Close transport to prevent memory leaks\n  c.res.raw.on('close', () => transport.close());\n\n  await server.connect(transport);\n  await transport.handleRequest(c.req.raw, c.res.raw, await c.req.json());\n  return c.body(null);\n});\n\nexport default app;\n```\n\n### 3. Deploy\n\n```bash\nwrangler deploy\n```\n\n### 4. Use Production Templates\n\n**For complete implementations**, copy from `templates\u002F` directory:\n- `templates\u002Fbasic-mcp-server.ts` - Minimal working server\n- `templates\u002Ftool-server.ts` - Multiple tools (API integrations, calculations)\n- `templates\u002Fresource-server.ts` - Static and dynamic resources\n- `templates\u002Ffull-server.ts` - Complete server (tools + resources + prompts)\n- `templates\u002Fauthenticated-server.ts` - Production security with API key authentication\n- `templates\u002Fwrangler.jsonc` - Cloudflare Workers configuration\n\n---\n\n## Authentication Patterns\n\n**Quick Example** - API Key Authentication (Most Common):\n\n```typescript\napp.use('\u002Fmcp', async (c, next) => {\n  const authHeader = c.req.header('Authorization');\n  if (!authHeader?.startsWith('Bearer ')) {\n    return c.json({ error: 'Unauthorized' }, 401);\n  }\n\n  const apiKey = authHeader.replace('Bearer ', '');\n  const isValid = await c.env.MCP_API_KEYS.get(`key:${apiKey}`);\n  if (!isValid) return c.json({ error: 'Invalid API key' }, 403);\n\n  await next();\n});\n```\n\n**For complete authentication guide**: Load `references\u002Fauthentication-guide.md` when implementing production authentication. Covers 5 methods: API Key (recommended), Cloudflare Zero Trust Access, OAuth 2.0, JWT custom, and mTLS. Includes security best practices, testing strategies, and migration guides.\n\n---\n\n## Cloudflare Service Integration\n\n**Quick Example** - D1 Database Tool:\n\n```typescript\nserver.registerTool(\n  'query-database',\n  {\n    description: 'Executes SQL query on D1 database',\n    inputSchema: z.object({\n      query: z.string(),\n      params: z.array(z.union([z.string(), z.number()])).optional()\n    })\n  },\n  async ({ query, params }, env) => {\n    const result = await env.DB.prepare(query).bind(...(params || [])).all();\n    return { content: [{ type: 'text', text: JSON.stringify(result.results, null, 2) }] };\n  }\n);\n```\n\n**Supported Services**: D1 (SQL Database), KV (Key-Value Store), R2 (Object Storage), Vectorize (Vector Database), Workers AI, Queues, Analytics Engine.\n\n**For complete integration guide**: Load `references\u002Fcloudflare-integration.md` when integrating Cloudflare services. Includes setup, MCP tool examples, best practices, and advanced patterns (RAG systems, combining services).\n\n---\n\n## Testing Strategies\n\n**Quick Testing Workflow**:\n\n1. **Unit Tests** (Vitest): Test tool logic in isolation\n2. **Integration Tests** (MCP Inspector): Test with `bunx @modelcontextprotocol\u002Finspector`\n3. **E2E Tests**: Test with real MCP clients\n\n```bash\n# Local dev\nnpm run dev\n\n# Test with Inspector\nbunx @modelcontextprotocol\u002Finspector\n```\n\n**For complete testing guide**: Load `references\u002Ftesting-guide.md` when writing tests. Covers unit testing with Vitest, integration testing with MCP Inspector, E2E testing, authentication testing, load testing with Artillery, mocking external APIs, and CI\u002FCD testing patterns.\n\n---\n\n## Known Issues Prevention\n\nThis skill prevents **13 documented errors**. Here are the **top 5 most critical**:\n\n### Issue #1: Export Syntax Issues (CRITICAL)\n**Error**: `\"Cannot read properties of undefined (reading 'map')\"`\n**Source**: honojs\u002Fhono#3955\n**Prevention**:\n```typescript\n\u002F\u002F ❌ WRONG                      \u002F\u002F ✅ CORRECT\nexport default { fetch: app.fetch };    export default app;\n```\n\n### Issue #2: Unclosed Transport Connections\n**Error**: Memory leaks, hanging connections\n**Prevention**:\n```typescript\napp.post('\u002Fmcp', async (c) => {\n  const transport = new StreamableHTTPServerTransport({...});\n  c.res.raw.on('close', () => transport.close()); \u002F\u002F CRITICAL\n  \u002F\u002F ... handle request\n});\n```\n\n### Issue #3: Tool Schema Validation Failure\n**Error**: `ListTools request handler fails to generate inputSchema`\n**Source**: modelcontextprotocol\u002Ftypescript-sdk#1028\n**Prevention**: Pass Zod schema directly - SDK handles conversion automatically\n```typescript\nserver.registerTool('tool', { inputSchema: z.object({...}) }, handler);\n```\n\n### Issue #4: Tool Arguments Not Passed to Handler\n**Error**: Handler receives `undefined` arguments\n**Source**: modelcontextprotocol\u002Ftypescript-sdk#1026\n**Prevention**: Use `z.infer\u003Ctypeof schema>` for type-safe handler parameters\n\n### Issue #5: CORS Misconfiguration\n**Error**: Browser clients can't connect\n**Prevention**:\n```typescript\nimport { cors } from 'hono\u002Fcors';\napp.use('\u002Fmcp', cors({ origin: ['http:\u002F\u002Flocalhost:3000'], allowMethods: ['POST', 'OPTIONS'] }));\n```\n\n**For complete error catalog**: Load `references\u002Fcommon-errors.md` when debugging. Covers all 13 errors with detailed solutions, root causes from GitHub issues, and debugging checklist.\n\n---\n\n## Deployment Workflow\n\n**Quick Deployment**:\n\n```bash\n# Local development\nnpm run dev  # Server at http:\u002F\u002Flocalhost:8787\u002Fmcp\n\n# Production\nnpm run build\nwrangler deploy\n\n# Specific environment\nwrangler deploy --env production\n```\n\n**For complete deployment guide**: Load `references\u002Fdeployment-guide.md` when setting up production. Covers environment setup (dev\u002Fstaging\u002Fprod), multiple environments, custom domains, CI\u002FCD with GitHub Actions, database migrations, monitoring & logs, rollback strategy, performance optimization, health checks, cost optimization, security checklist, and troubleshooting.\n\n---\n\n## Package Versions (Verified 2025-10-28)\n\n```json\n{\n  \"dependencies\": {\n    \"@modelcontextprotocol\u002Fsdk\": \"^1.20.2\",\n    \"@cloudflare\u002Fworkers-types\": \"^4.20251011.0\",\n    \"hono\": \"^4.10.1\",\n    \"zod\": \"^4.1.12\"\n  },\n  \"devDependencies\": {\n    \"@cloudflare\u002Fvitest-pool-workers\": \"^0.5.29\",\n    \"vitest\": \"^3.0.0\",\n    \"wrangler\": \"^4.43.0\",\n    \"typescript\": \"^5.7.0\"\n  }\n}\n```\n\n---\n\n## When to Use Cloudflare Agents SDK Instead\n\nUse **Cloudflare Agents MCP** when you need:\n- **Stateful agents** with persistent storage (SQLite up to 1GB)\n- **WebSocket support** for real-time bidirectional communication\n- **Long-running sessions** with conversation history\n- **Scheduled agent tasks** with Durable Objects alarms\n- **Global distribution** with automatic state replication\n\nUse **this skill (standalone TypeScript MCP)** when you need:\n- **Stateless tools** and API integrations\n- **Edge deployment** with minimal cold start latency\n- **Simple authentication** (API keys, OAuth)\n- **Pay-per-request pricing** (no Durable Objects overhead)\n- **Maximum portability** (works on any platform, not just Cloudflare)\n\nSee `references\u002Fcloudflare-agents-vs-standalone.md` for detailed comparison.\n\n---\n\n## When to Load References\n\nLoad reference files when working on specific aspects of TypeScript MCP servers:\n\n### authentication-guide.md\nLoad when:\n- **Setup-based**: Implementing authentication for production MCP server\n- **Method-based**: Choosing between API Key, OAuth 2.0, Zero Trust, JWT, or mTLS\n- **Security-based**: Implementing rate limiting, API key rotation, audit logging\n- **Testing-based**: Writing authentication tests (unit, integration, E2E)\n- **Migration-based**: Upgrading from one auth method to another\n\n### cloudflare-agents-vs-standalone.md\nLoad when:\n- **Decision-based**: Choosing between standalone MCP and Cloudflare Agents SDK\n- **Architecture-based**: Need stateful agents vs stateless tools\n- **Cost-based**: Comparing pricing for low\u002Fhigh traffic scenarios\n- **Feature-based**: Need WebSockets, persistent storage, or scheduled tasks\n- **Migration-based**: Moving from standalone to Agents SDK or vice versa\n\n### cloudflare-integration.md\nLoad when:\n- **Service-based**: Integrating D1, KV, R2, Vectorize, Workers AI, Queues, or Analytics Engine\n- **Pattern-based**: Building RAG systems or multi-service applications\n- **Setup-based**: Configuring wrangler.jsonc bindings for Cloudflare services\n- **Example-based**: Need working code for specific service integration\n\n### common-errors.md\nLoad when:\n- **Error-based**: Encountering any of the 13 documented errors\n- **Debugging-based**: Server not working, need systematic debugging checklist\n- **Prevention-based**: Want to prevent all known issues before deployment\n- **Source-based**: Need GitHub issue references for specific errors\n\n### deployment-guide.md\nLoad when:\n- **CI\u002FCD-based**: Setting up GitHub Actions for automated deployment\n- **Environment-based**: Configuring staging\u002Fproduction environments\n- **Migration-based**: Running D1 database migrations in CI\u002FCD\n- **Monitoring-based**: Setting up logs, analytics, health checks\n- **Optimization-based**: Implementing caching, performance optimization, cost reduction\n\n### testing-guide.md\nLoad when:\n- **Testing-based**: Writing unit tests, integration tests, or E2E tests\n- **Tool-based**: Using Vitest, MCP Inspector, or Artillery for testing\n- **CI\u002FCD-based**: Setting up automated testing in GitHub Actions\n- **Authentication-based**: Testing authentication middleware\n- **Load-based**: Need to load test MCP server endpoints\n\n### tool-patterns.md\nLoad when:\n- **Pattern-based**: Implementing external API wrappers, database queries, file operations\n- **Example-based**: Need production-tested tool implementation examples\n- **Architecture-based**: Building multi-step operations, streaming responses, caching tools\n- **Error-based**: Need error handling best practices for tools\n- **Response-based**: Understanding tool response formats\n\n---\n\n## Using Bundled Resources\n\n**Templates** (`templates\u002F`): Production-ready implementations\n- `basic-mcp-server.ts` - Minimal working server\n- `tool-server.ts` - Multiple tools (API integrations)\n- `resource-server.ts` - Static and dynamic resources\n- `full-server.ts` - Complete server (tools + resources + prompts)\n- `authenticated-server.ts` - Production security\n- `wrangler.jsonc` - Cloudflare Workers configuration\n\n**Reference Guides** (`references\u002F`): Comprehensive documentation (see \"When to Load References\" section above)\n- `tool-patterns.md` - Implementation patterns\n- `authentication-guide.md` - All 5 auth methods\n- `testing-guide.md` - Unit, integration, E2E testing\n- `deployment-guide.md` - CI\u002FCD, environments, monitoring\n- `cloudflare-integration.md` - D1, KV, R2, Vectorize, Workers AI\n- `common-errors.md` - All 13 errors + debugging\n- `cloudflare-agents-vs-standalone.md` - Decision matrix\n\n**Scripts** (`scripts\u002F`): Automation tools\n- `init-mcp-server.sh` - Initialize new project\n- `test-mcp-connection.sh` - Test server connectivity\n\n---\n\n## Official Documentation\n\n- **MCP Specification**: https:\u002F\u002Fspec.modelcontextprotocol.io\u002F\n- **TypeScript SDK**: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\n- **Cloudflare Workers**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkers\u002F\n- **Hono Framework**: https:\u002F\u002Fhono.dev\u002F\n- **Context7 Library ID**: `\u002Fwebsites\u002Fmodelcontextprotocol` (if available)\n\n**Example Servers**:\n- Official examples: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\n- Cloudflare MCP server: https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fmcp-server-cloudflare\n\n---\n\n## Critical Rules\n\n**Always Do**:\n✅ Close transport on response end | ✅ Use `export default app` syntax | ✅ Implement authentication | ✅ Add rate limiting | ✅ Use Zod schemas | ✅ Test with MCP Inspector | ✅ Update to SDK v1.20.2+ | ✅ Document all tools | ✅ Handle errors gracefully | ✅ Use environment variables\n\n**Never Do**:\n❌ Object wrapper export | ❌ Forget to close transport | ❌ Deploy without auth | ❌ Log env variables | ❌ Use CommonJS | ❌ Skip CORS config | ❌ Hardcode credentials | ❌ Return raw errors | ❌ Deploy untested | ❌ Use outdated SDK\n\n---\n\n## Complete Setup Checklist\n\nUse this checklist to verify your MCP server setup:\n\n- [ ] SDK version is 1.20.2 or later\n- [ ] Export syntax is correct (direct export, not object wrapper)\n- [ ] Transport is closed on response end\n- [ ] Authentication is implemented (if production)\n- [ ] Rate limiting is configured (if public-facing)\n- [ ] CORS headers are set (if browser clients)\n- [ ] All tools have clear descriptions and Zod schemas\n- [ ] Environment variables are used for secrets\n- [ ] wrangler.jsonc includes all necessary bindings\n- [ ] Local testing with `wrangler dev` succeeds\n- [ ] MCP Inspector can connect and list tools\n- [ ] Production deployment succeeds\n- [ ] All tools\u002Fresources return expected responses\n\n---\n\n## Production Example\n\nThis skill is based on patterns from:\n- **Official MCP TypeScript SDK examples**: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\n- **Cloudflare MCP server**: https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fmcp-server-cloudflare\n- **Errors**: 0 (all 10+ known issues prevented)\n- **Token Savings**: ~70% vs manual implementation\n- **Validation**: ✅ All templates tested on Cloudflare Workers\n\n---\n\n**Questions? Issues?**\n\n1. Check `references\u002Fcommon-errors.md` for troubleshooting\n2. Verify all steps in the Quick Start section\n3. Test with MCP Inspector: `bunx @modelcontextprotocol\u002Finspector`\n4. Check official docs: https:\u002F\u002Fspec.modelcontextprotocol.io\u002F\n5. Ensure SDK version is 1.20.2 or later\n\n---\n\n**Last Updated**: 2025-10-28\n**SDK Version**: @modelcontextprotocol\u002Fsdk@1.20.2\n**Maintainer**: Claude Skills Repository\n","# TypeScript MCP Server on Cloudflare Workers\n\nBuild production-ready Model Context Protocol (MCP) servers using TypeScript and deploy them on Cloudflare Workers. This skill covers the official `@modelcontextprotocol\u002Fsdk`, HTTP transport setup, authentication patterns, Cloudflare service integrations, and comprehensive error prevention.\n\n---\n\n## When to Use This Skill\n\nUse this skill when:\n- Building **MCP servers** to expose APIs, tools, or data to LLMs\n- Deploying **serverless MCP endpoints** on Cloudflare Workers\n- Integrating **external APIs** as MCP tools (REST, GraphQL, databases)\n- Creating **stateless MCP servers** for edge deployment\n- Exposing **Cloudflare services** (D1, KV, R2, Vectorize) via MCP protocol\n- Implementing **authenticated MCP servers** with API keys, OAuth, or Zero Trust\n- Building **multi-tool MCP servers** with resources and prompts\n- Needing **production-ready templates** that prevent common MCP errors\n\n**Do NOT use this skill when**:\n- Building **Python MCP servers** (use FastMCP skill instead)\n- Needing **stateful agents** with WebSockets (use Cloudflare Agents SDK)\n- Wanting **long-running persistent agents** with SQLite storage (use Durable Objects)\n- Building **local CLI tools** (use stdio transport, not HTTP)\n\n---\n\n## Secure Installation\n\nMCP server packages grant tool access to LLMs — a compromised SDK can expose full system control. Verify packages before installing. Follow supply chain security best practices:\n\n- **Block post-install scripts** — `npm config set ignore-scripts true` (or Bun: disabled by default)\n- **Cooldown period** — Wait 7 days for new package versions to be vetted by the community\n- **Audit before installing** — Run `socket package score npm \u003Cpkg>` or use `socket npm install \u003Cpkg>` to check packages\n\nLoad the `dependency-upgrade` skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.\n\n## Core Concepts\n\n**MCP Protocol Components**:\n\n1. **Tools** - Functions LLMs can invoke (Zod schemas, async handlers, external APIs)\n2. **Resources** - Data exposure (URI-based: `config:\u002F\u002Fapp`, `user:\u002F\u002F{userId}`)\n3. **Prompts** - Pre-configured templates for LLM interactions\n4. **Completions** - Argument auto-complete (optional)\n\n---\n\n## Quick Start\n\n### 1. Install Dependencies\n\n```bash\nbun add @modelcontextprotocol\u002Fsdk hono zod\nbun add -d @cloudflare\u002Fworkers-types wrangler typescript\n```\n\n### 2. Create Basic MCP Server\n\n```typescript\nimport { McpServer } from '@modelcontextprotocol\u002Fsdk\u002Fserver\u002Fmcp.js';\nimport { StreamableHTTPServerTransport } from '@modelcontextprotocol\u002Fsdk\u002Fserver\u002FstreamableHttp.js';\nimport { Hono } from 'hono';\nimport { z } from 'zod';\n\nconst server = new McpServer({ name: 'my-mcp-server', version: '1.0.0' });\n\n\u002F\u002F Register a tool\nserver.registerTool(\n  'echo',\n  {\n    description: 'Echoes back the input text',\n    inputSchema: z.object({ text: z.string().describe('Text to echo') })\n  },\n  async ({ text }) => ({ content: [{ type: 'text', text }] })\n);\n\n\u002F\u002F HTTP endpoint\nconst app = new Hono();\n\napp.post('\u002Fmcp', async (c) => {\n  const transport = new StreamableHTTPServerTransport({\n    sessionIdGenerator: undefined,\n    enableJsonResponse: true\n  });\n\n  \u002F\u002F CRITICAL: Close transport to prevent memory leaks\n  c.res.raw.on('close', () => transport.close());\n\n  await server.connect(transport);\n  await transport.handleRequest(c.req.raw, c.res.raw, await c.req.json());\n  return c.body(null);\n});\n\nexport default app;\n```\n\n### 3. Deploy\n\n```bash\nwrangler deploy\n```\n\n### 4. Use Production Templates\n\n**For complete implementations**, copy from `templates\u002F` directory:\n- `templates\u002Fbasic-mcp-server.ts` - Minimal working server\n- `templates\u002Ftool-server.ts` - Multiple tools (API integrations, calculations)\n- `templates\u002Fresource-server.ts` - Static and dynamic resources\n- `templates\u002Ffull-server.ts` - Complete server (tools + resources + prompts)\n- `templates\u002Fauthenticated-server.ts` - Production security with API key authentication\n- `templates\u002Fwrangler.jsonc` - Cloudflare Workers configuration\n\n---\n\n## Authentication Patterns\n\n**Quick Example** - API Key Authentication (Most Common):\n\n```typescript\napp.use('\u002Fmcp', async (c, next) => {\n  const authHeader = c.req.header('Authorization');\n  if (!authHeader?.startsWith('Bearer ')) {\n    return c.json({ error: 'Unauthorized' }, 401);\n  }\n\n  const apiKey = authHeader.replace('Bearer ', '');\n  const isValid = await c.env.MCP_API_KEYS.get(`key:${apiKey}`);\n  if (!isValid) return c.json({ error: 'Invalid API key' }, 403);\n\n  await next();\n});\n```\n\n**For complete authentication guide**: Load `references\u002Fauthentication-guide.md` when implementing production authentication. Covers 5 methods: API Key (recommended), Cloudflare Zero Trust Access, OAuth 2.0, JWT custom, and mTLS. Includes security best practices, testing strategies, and migration guides.\n\n---\n\n## Cloudflare Service Integration\n\n**Quick Example** - D1 Database Tool:\n\n```typescript\nserver.registerTool(\n  'query-database',\n  {\n    description: 'Executes SQL query on D1 database',\n    inputSchema: z.object({\n      query: z.string(),\n      params: z.array(z.union([z.string(), z.number()])).optional()\n    })\n  },\n  async ({ query, params }, env) => {\n    const result = await env.DB.prepare(query).bind(...(params || [])).all();\n    return { content: [{ type: 'text', text: JSON.stringify(result.results, null, 2) }] };\n  }\n);\n```\n\n**Supported Services**: D1 (SQL Database), KV (Key-Value Store), R2 (Object Storage), Vectorize (Vector Database), Workers AI, Queues, Analytics Engine.\n\n**For complete integration guide**: Load `references\u002Fcloudflare-integration.md` when integrating Cloudflare services. Includes setup, MCP tool examples, best practices, and advanced patterns (RAG systems, combining services).\n\n---\n\n## Testing Strategies\n\n**Quick Testing Workflow**:\n\n1. **Unit Tests** (Vitest): Test tool logic in isolation\n2. **Integration Tests** (MCP Inspector): Test with `bunx @modelcontextprotocol\u002Finspector`\n3. **E2E Tests**: Test with real MCP clients\n\n```bash\n# Local dev\nnpm run dev\n\n# Test with Inspector\nbunx @modelcontextprotocol\u002Finspector\n```\n\n**For complete testing guide**: Load `references\u002Ftesting-guide.md` when writing tests. Covers unit testing with Vitest, integration testing with MCP Inspector, E2E testing, authentication testing, load testing with Artillery, mocking external APIs, and CI\u002FCD testing patterns.\n\n---\n\n## Known Issues Prevention\n\nThis skill prevents **13 documented errors**. Here are the **top 5 most critical**:\n\n### Issue #1: Export Syntax Issues (CRITICAL)\n**Error**: `\"Cannot read properties of undefined (reading 'map')\"`\n**Source**: honojs\u002Fhono#3955\n**Prevention**:\n```typescript\n\u002F\u002F ❌ WRONG                      \u002F\u002F ✅ CORRECT\nexport default { fetch: app.fetch };    export default app;\n```\n\n### Issue #2: Unclosed Transport Connections\n**Error**: Memory leaks, hanging connections\n**Prevention**:\n```typescript\napp.post('\u002Fmcp', async (c) => {\n  const transport = new StreamableHTTPServerTransport({...});\n  c.res.raw.on('close', () => transport.close()); \u002F\u002F CRITICAL\n  \u002F\u002F ... handle request\n});\n```\n\n### Issue #3: Tool Schema Validation Failure\n**Error**: `ListTools request handler fails to generate inputSchema`\n**Source**: modelcontextprotocol\u002Ftypescript-sdk#1028\n**Prevention**: Pass Zod schema directly - SDK handles conversion automatically\n```typescript\nserver.registerTool('tool', { inputSchema: z.object({...}) }, handler);\n```\n\n### Issue #4: Tool Arguments Not Passed to Handler\n**Error**: Handler receives `undefined` arguments\n**Source**: modelcontextprotocol\u002Ftypescript-sdk#1026\n**Prevention**: Use `z.infer\u003Ctypeof schema>` for type-safe handler parameters\n\n### Issue #5: CORS Misconfiguration\n**Error**: Browser clients can't connect\n**Prevention**:\n```typescript\nimport { cors } from 'hono\u002Fcors';\napp.use('\u002Fmcp', cors({ origin: ['http:\u002F\u002Flocalhost:3000'], allowMethods: ['POST', 'OPTIONS'] }));\n```\n\n**For complete error catalog**: Load `references\u002Fcommon-errors.md` when debugging. Covers all 13 errors with detailed solutions, root causes from GitHub issues, and debugging checklist.\n\n---\n\n## Deployment Workflow\n\n**Quick Deployment**:\n\n```bash\n# Local development\nnpm run dev  # Server at http:\u002F\u002Flocalhost:8787\u002Fmcp\n\n# Production\nnpm run build\nwrangler deploy\n\n# Specific environment\nwrangler deploy --env production\n```\n\n**For complete deployment guide**: Load `references\u002Fdeployment-guide.md` when setting up production. Covers environment setup (dev\u002Fstaging\u002Fprod), multiple environments, custom domains, CI\u002FCD with GitHub Actions, database migrations, monitoring & logs, rollback strategy, performance optimization, health checks, cost optimization, security checklist, and troubleshooting.\n\n---\n\n## Package Versions (Verified 2025-10-28)\n\n```json\n{\n  \"dependencies\": {\n    \"@modelcontextprotocol\u002Fsdk\": \"^1.20.2\",\n    \"@cloudflare\u002Fworkers-types\": \"^4.20251011.0\",\n    \"hono\": \"^4.10.1\",\n    \"zod\": \"^4.1.12\"\n  },\n  \"devDependencies\": {\n    \"@cloudflare\u002Fvitest-pool-workers\": \"^0.5.29\",\n    \"vitest\": \"^3.0.0\",\n    \"wrangler\": \"^4.43.0\",\n    \"typescript\": \"^5.7.0\"\n  }\n}\n```\n\n---\n\n## When to Use Cloudflare Agents SDK Instead\n\nUse **Cloudflare Agents MCP** when you need:\n- **Stateful agents** with persistent storage (SQLite up to 1GB)\n- **WebSocket support** for real-time bidirectional communication\n- **Long-running sessions** with conversation history\n- **Scheduled agent tasks** with Durable Objects alarms\n- **Global distribution** with automatic state replication\n\nUse **this skill (standalone TypeScript MCP)** when you need:\n- **Stateless tools** and API integrations\n- **Edge deployment** with minimal cold start latency\n- **Simple authentication** (API keys, OAuth)\n- **Pay-per-request pricing** (no Durable Objects overhead)\n- **Maximum portability** (works on any platform, not just Cloudflare)\n\nSee `references\u002Fcloudflare-agents-vs-standalone.md` for detailed comparison.\n\n---\n\n## When to Load References\n\nLoad reference files when working on specific aspects of TypeScript MCP servers:\n\n### authentication-guide.md\nLoad when:\n- **Setup-based**: Implementing authentication for production MCP server\n- **Method-based**: Choosing between API Key, OAuth 2.0, Zero Trust, JWT, or mTLS\n- **Security-based**: Implementing rate limiting, API key rotation, audit logging\n- **Testing-based**: Writing authentication tests (unit, integration, E2E)\n- **Migration-based**: Upgrading from one auth method to another\n\n### cloudflare-agents-vs-standalone.md\nLoad when:\n- **Decision-based**: Choosing between standalone MCP and Cloudflare Agents SDK\n- **Architecture-based**: Need stateful agents vs stateless tools\n- **Cost-based**: Comparing pricing for low\u002Fhigh traffic scenarios\n- **Feature-based**: Need WebSockets, persistent storage, or scheduled tasks\n- **Migration-based**: Moving from standalone to Agents SDK or vice versa\n\n### cloudflare-integration.md\nLoad when:\n- **Service-based**: Integrating D1, KV, R2, Vectorize, Workers AI, Queues, or Analytics Engine\n- **Pattern-based**: Building RAG systems or multi-service applications\n- **Setup-based**: Configuring wrangler.jsonc bindings for Cloudflare services\n- **Example-based**: Need working code for specific service integration\n\n### common-errors.md\nLoad when:\n- **Error-based**: Encountering any of the 13 documented errors\n- **Debugging-based**: Server not working, need systematic debugging checklist\n- **Prevention-based**: Want to prevent all known issues before deployment\n- **Source-based**: Need GitHub issue references for specific errors\n\n### deployment-guide.md\nLoad when:\n- **CI\u002FCD-based**: Setting up GitHub Actions for automated deployment\n- **Environment-based**: Configuring staging\u002Fproduction environments\n- **Migration-based**: Running D1 database migrations in CI\u002FCD\n- **Monitoring-based**: Setting up logs, analytics, health checks\n- **Optimization-based**: Implementing caching, performance optimization, cost reduction\n\n### testing-guide.md\nLoad when:\n- **Testing-based**: Writing unit tests, integration tests, or E2E tests\n- **Tool-based**: Using Vitest, MCP Inspector, or Artillery for testing\n- **CI\u002FCD-based**: Setting up automated testing in GitHub Actions\n- **Authentication-based**: Testing authentication middleware\n- **Load-based**: Need to load test MCP server endpoints\n\n### tool-patterns.md\nLoad when:\n- **Pattern-based**: Implementing external API wrappers, database queries, file operations\n- **Example-based**: Need production-tested tool implementation examples\n- **Architecture-based**: Building multi-step operations, streaming responses, caching tools\n- **Error-based**: Need error handling best practices for tools\n- **Response-based**: Understanding tool response formats\n\n---\n\n## Using Bundled Resources\n\n**Templates** (`templates\u002F`): Production-ready implementations\n- `basic-mcp-server.ts` - Minimal working server\n- `tool-server.ts` - Multiple tools (API integrations)\n- `resource-server.ts` - Static and dynamic resources\n- `full-server.ts` - Complete server (tools + resources + prompts)\n- `authenticated-server.ts` - Production security\n- `wrangler.jsonc` - Cloudflare Workers configuration\n\n**Reference Guides** (`references\u002F`): Comprehensive documentation (see \"When to Load References\" section above)\n- `tool-patterns.md` - Implementation patterns\n- `authentication-guide.md` - All 5 auth methods\n- `testing-guide.md` - Unit, integration, E2E testing\n- `deployment-guide.md` - CI\u002FCD, environments, monitoring\n- `cloudflare-integration.md` - D1, KV, R2, Vectorize, Workers AI\n- `common-errors.md` - All 13 errors + debugging\n- `cloudflare-agents-vs-standalone.md` - Decision matrix\n\n**Scripts** (`scripts\u002F`): Automation tools\n- `init-mcp-server.sh` - Initialize new project\n- `test-mcp-connection.sh` - Test server connectivity\n\n---\n\n## Official Documentation\n\n- **MCP Specification**: https:\u002F\u002Fspec.modelcontextprotocol.io\u002F\n- **TypeScript SDK**: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk\n- **Cloudflare Workers**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkers\u002F\n- **Hono Framework**: https:\u002F\u002Fhono.dev\u002F\n- **Context7 Library ID**: `\u002Fwebsites\u002Fmodelcontextprotocol` (if available)\n\n**Example Servers**:\n- Official examples: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\n- Cloudflare MCP server: https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fmcp-server-cloudflare\n\n---\n\n## Critical Rules\n\n**Always Do**:\n✅ Close transport on response end | ✅ Use `export default app` syntax | ✅ Implement authentication | ✅ Add rate limiting | ✅ Use Zod schemas | ✅ Test with MCP Inspector | ✅ Update to SDK v1.20.2+ | ✅ Document all tools | ✅ Handle errors gracefully | ✅ Use environment variables\n\n**Never Do**:\n❌ Object wrapper export | ❌ Forget to close transport | ❌ Deploy without auth | ❌ Log env variables | ❌ Use CommonJS | ❌ Skip CORS config | ❌ Hardcode credentials | ❌ Return raw errors | ❌ Deploy untested | ❌ Use outdated SDK\n\n---\n\n## Complete Setup Checklist\n\nUse this checklist to verify your MCP server setup:\n\n- [ ] SDK version is 1.20.2 or later\n- [ ] Export syntax is correct (direct export, not object wrapper)\n- [ ] Transport is closed on response end\n- [ ] Authentication is implemented (if production)\n- [ ] Rate limiting is configured (if public-facing)\n- [ ] CORS headers are set (if browser clients)\n- [ ] All tools have clear descriptions and Zod schemas\n- [ ] Environment variables are used for secrets\n- [ ] wrangler.jsonc includes all necessary bindings\n- [ ] Local testing with `wrangler dev` succeeds\n- [ ] MCP Inspector can connect and list tools\n- [ ] Production deployment succeeds\n- [ ] All tools\u002Fresources return expected responses\n\n---\n\n## Production Example\n\nThis skill is based on patterns from:\n- **Official MCP TypeScript SDK examples**: https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\n- **Cloudflare MCP server**: https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fmcp-server-cloudflare\n- **Errors**: 0 (all 10+ known issues prevented)\n- **Token Savings**: ~70% vs manual implementation\n- **Validation**: ✅ All templates tested on Cloudflare Workers\n\n---\n\n**Questions? Issues?**\n\n1. Check `references\u002Fcommon-errors.md` for troubleshooting\n2. Verify all steps in the Quick Start section\n3. Test with MCP Inspector: `bunx @modelcontextprotocol\u002Finspector`\n4. Check official docs: https:\u002F\u002Fspec.modelcontextprotocol.io\u002F\n5. Ensure SDK version is 1.20.2 or later\n\n---\n\n**Last Updated**: 2025-10-28\n**SDK Version**: @modelcontextprotocol\u002Fsdk@1.20.2\n**Maintainer**: Claude Skills Repository\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":62},{"version":25,"keywords":26,"platform":56,"sdk_version":57,"last_updated":58,"token_savings":59,"errors_prevented":60,"optimization_date":58,"production_tested":61},"2.0.0",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55],"mcp","model context protocol","typescript mcp","cloudflare workers mcp","mcp server","mcp tools","mcp resources","mcp sdk","@modelcontextprotocol\u002Fsdk","hono mcp","streamablehttpservertransport","mcp authentication","mcp cloudflare","edge mcp server","serverless mcp","typescript mcp server","mcp api","llm tools","ai tools","cloudflare d1 mcp","cloudflare kv mcp","mcp testing","mcp deployment","wrangler mcp","export syntax error","schema validation error","memory leak mcp","cors mcp","rate limiting mcp","cloudflare-workers","@modelcontextprotocol\u002Fsdk@1.22.0",1765929600000,"~55%",13,true,[63,64,65,66,67,68],"Read","Write","Edit","Bash","Grep","Glob","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":61},[77,80,83],{"tool":78,"command":79},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill typescript-mcp",{"tool":81,"command":82},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill typescript-mcp",{"tool":84,"command":85},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill typescript-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002FSKILL.md",[88,94,98,102,106,110,114,118,124,128,132,136,140,144,148],{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fauthentication-guide.md","REFERENCE","参考文档",10805,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Fauthentication-guide.md",{"path":95,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fcloudflare-agents-vs-standalone.md",5704,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Fcloudflare-agents-vs-standalone.md",{"path":99,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fcloudflare-integration.md",9168,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Fcloudflare-integration.md",{"path":103,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fcommon-errors.md",12156,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Fcommon-errors.md",{"path":107,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fdeployment-guide.md",6434,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Fdeployment-guide.md",{"path":111,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Ftesting-guide.md",6754,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Ftesting-guide.md",{"path":115,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Ftool-patterns.md",8623,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Freferences\u002Ftool-patterns.md",{"path":119,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Finit-mcp-server.sh","SCRIPT","脚本",4612,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Fscripts\u002Finit-mcp-server.sh",{"path":125,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Ftest-mcp-connection.sh",4189,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Fscripts\u002Ftest-mcp-connection.sh",{"path":129,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":130,"sourceHtmlUrl":131},"templates\u002Fauthenticated-server.ts",5632,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Fauthenticated-server.ts",{"path":133,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":134,"sourceHtmlUrl":135},"templates\u002Fbasic-mcp-server.ts",2435,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Fbasic-mcp-server.ts",{"path":137,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":138,"sourceHtmlUrl":139},"templates\u002Ffull-server.ts",8190,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Ffull-server.ts",{"path":141,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":142,"sourceHtmlUrl":143},"templates\u002Fresource-server.ts",7683,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Fresource-server.ts",{"path":145,"resourceType":120,"resourceTypeDesc":121,"sizeBytes":146,"sourceHtmlUrl":147},"templates\u002Ftool-server.ts",7129,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Ftool-server.ts",{"path":149,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":152,"sourceHtmlUrl":153},"templates\u002Fwrangler.jsonc","OTHER","其他",3857,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Ftypescript-mcp\u002Fskills\u002Ftypescript-mcp\u002Ftemplates\u002Fwrangler.jsonc",[155,163,170,177,184,191],{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":159,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]