1,760 tagged model-context-protocol, measured the same way as everything else here.
Browse within: fastmcp 57cloudflare-workers 37nextjs 36docker 31llm-tools 29bun 27browser-automation 23bioinformatics 22claude-ai 22github-copilot 21local-first 21markdown 21self-hosted 21claude-desktop 20
Instructions file
Repository instructions for an MCP server that lets a non-visual AI model analyze images through a configured OpenAI-compatible vision service. MCP is a connection format for exposing tools to AI clients.
Instructions file CodexOpenCode
AGENTS.md instructions for gethelio/helio, covering helio, architecture, monorepo structure, tech stack and commands.
Instructions file CodexOpenCode
AGENTS.md instructions for nickschuetz/o3de-mcp, covering agent guide — o3de-mcp, quick start decision tree, token efficiency rules, 1. batch over individual calls and 2. query before modifying.
Instructions file
Claude Code instructions for nickschuetz/o3de-mcp, covering claude.md, what this is, commands, install (editable, with dev tools) and run the mcp server.
Instructions file CodexOpenCode
AGENTS.md instructions for greynewell/mcpbr, covering agent guidelines for mcpbr development, virtual environment setup, option 1: using uv (recommended), run commands without installation and run python scripts/tests.
Instructions file
Claude Code instructions for greynewell/mcpbr, a project described as: Benchmark your MCP server.
Instructions file CodexOpenCode
Instructions for sumioshi/whatsapp-automation, covering instruções do projeto (codex e outros agentes), regras duras de envio (não negociáveis), redação de mensagem pra cliente, modo de envio por chat (confirmar vs autônomo) and mídia na nuvem (midiapendente) — não é erro.
Instructions file
Instructions for sumioshi/whatsapp-automation, covering vocabulário de acompanhamento (desambiguação), recipe do monitor de mensagem (sem zumbi), modo de envio por chat (confirmar vs autônomo), mídia na nuvem (midiapendente) — não é erro and grupo renomeado ≠ chat morto (slug é estável).
Instructions file CodexOpenCode
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
Instructions file
Instructions for LindaHaviv/second-brain: Read AGENTS.md — the agent instructions for this repo live there (rules, test/eval gates, and the sanctioned way to do common tasks). It applies to Claude Code and every other coding agent equally.
Instructions file
Instructions for ttpears/gitlab-mcp, covering claude.md, commands, architecture, project conventions (from .cursorrules) and release flow.
Instructions file
Instructions for evansims/openfga-mcp, covering claude.md, project overview, model context protocol concepts, development commands and linting and code quality.
Instructions file
Instructions for AryanBV/pdf-toolkit-mcp, covering pdf-toolkit-mcp, 1. project overview, 2. tech stack, 3. project structure and 4. mcp sdk patterns.
Instructions file CodexOpenCode
AGENTS.md instructions for Himanshu507/cgcone: This version has breaking changes - APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ before writing any code. Heed deprecation notices.
Instructions file
Claude Code instructions for Himanshu507/cgcone, a project described as: npm for AI CLIs - install MCP servers across Claude Code, Gemini CLI, Codex, Copilot.
ankit-verma-209171/android-docs-mcp
Instructions file CodexOpenCode
Instructions for ankit-verma-209171/android-docs-mcp, covering agents.md, project overview, working agreements, source layout and build and validation.
Instructions file
Claude Code instructions for jsulmont/mcp-lisp, covering mcp-lisp — project guide, build & test, lisp conventions, testing conventions and spec-first workflow.
like-a-freedom/rusty_apple_mail_mcp
Instructions file CodexOpenCode
AGENTS.md instructions for like-a-freedom/rusty_apple_mail_mcp, covering agents.md — rust development constitution, code navigation rules, 0. meta-rules for ai agents, quality gate (mandatory before every commit) and 1. format — must pass before anything else.
Instructions file GitHub Copilot
Instructions for neozhehan/figma-edit-mcp: See the figma-edit skill (skills/figma-edit/SKILL.md) and the MCP resource guides (figma-edit://guide/) for the canonical rules, error-code taxonomy, and workflows. Treat them as authoritative; do not duplicate their content here.
Instructions file CodexOpenCode
Instructions for neozhehan/figma-edit-mcp: This server enforces hard safety constraints (scope locking, name verification, batch validation) that you cannot bypass, and it returns structured error codes you need to recover from. Do not operate blind — load the guidance before writing.
Instructions file
Instructions for neozhehan/figma-edit-mcp, a project described as: Read, create, and modify Figma designs programmatically via MCP, empowering AI to execute Figma changes safer, cleaner, and faster.
Instructions file CodexOpenCode
AGENTS.md instructions for cyanheads/secedgar-mcp-server, covering agent protocol, core rules, what's next?, mcp surface and tools.
Instructions file
Claude Code instructions for cyanheads/secedgar-mcp-server, covering agent protocol, core rules, what's next?, mcp surface and tools.
Instructions file GitHub Copilot
Copilot instructions for starloghq/index: ALWAYS consult the starlogsearch MCP tool before recommending or installing libraries for: authentication, email, background-jobs, feature-flags, caching, realtime, or orm-database.