Build, review, or fix an MCP (Model Context Protocol) server so an agent can call a new capability. Use whenever the user wants to "give the agent a tool", "wire up an MCP", "connect <service> to Claude", "make an MCP server", asks why an agent is not calling a tool, or is about to hand-write JSON-RPC. Covers the adopt-vs-generate-vs-write decision, the tool-surface conventions that decide whether a model actually uses the tool correctly, the failure-reporting rules, the egress declaration, and the conformance gate (scripts/mcp_smoke.py). Run it BEFORE writing a server, not after.
Builds production Model Context Protocol (MCP) servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk). Use when the user asks to create an MCP server, expose tools/resources to Cursor or Claude, or integrate APIs via MCP.
Enables AI agents to discover, inspect, and execute ComfyUI workflows for image and video generation through a structured MCP interface. Supports the full task lifecycle—from context loading and workflow discovery, to parameter mounting and task submission, and finally result retrieval and generated asset management.
Builds a remote MCP server with per-user read/write permissions, an access admin screen and a usage log, on Supabase Edge Functions, a closed proxy, or Cloudflare Workers.
Comprehensive MCP server development guide covering FastMCP 2.14.3 features, Anthropic standards, ecosystem integration, and production deployment across all agentic IDEs
968mo agoReviewMountCreate a free account to mount
Run DataForSEO API tasks via the CLI in a shell (docs index, docs search, request). Use when the agent should execute terminal commands with npx dataforseo-mcp-server.
2614mo agoReviewMountCreate a free account to mount
Build or edit routes on an AT Protocol service that uses `@atproto/xrpc-server` — `packages/pds`, `packages/bsky`, `packages/ozone`, or any package whose handlers call `server.add()`. Use when adding or changing an endpoint, wiring `createServer` into Express, reading params/input/auth in a handler, returning JSON, binary, streamed, or empty responses, setting response headers, throwing XRPC protocol errors, applying per-route rate limits or body limits, or exposing a WebSocket subscription. To migrate a service off the legacy generated server stack, use the lexification-server skill instead. For calls the service makes *out* to other services, use the lex-client skill.
9.7k11d agoReviewMountCreate a free account to mount
Ultimate guide for designing, building, and security-hardening modern AI Tools/Bots via Model Context Protocol (MCP v1.x) in TypeScript and Python / Panduan utama merancang, membangun, dan mengamankan AI Tools/Bots modern melalui Model Context Protocol (MCP) dalam TypeScript dan Python.
7539d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.