Annuaire des serveurs MCP
53,972 serveurs MCP qui relient les assistants IA à des outils et des données, issus du registre MCP officiel et des listes communautaires, mis à jour toutes les heures.
- 16 catégories
- 34,242 serveurs distants
- Mis à jour toutes les heures
redconio.github.natiixnt/redcon
Deterministic context packing for AI coding agents; measured 83% fewer input tokens, local.
Safeshipapp.safeship/mcp
API monitoring from your editor. Checks the JSON your endpoints return, not just the status code.
Axisdev.useaxis/axis
Coding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.
VOC OpenAPI MCPio.github.SolveaCX/voc-mcp
VOC OpenAPI gives AI agents authorized review and product data for insights, tagging, and listings.
LLM Sandboxio.github.vndee/llm-sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
LLM Usageio.github.zhaoyue722/llm-usage-mcp
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
RepoPilotapp.repopilot/repopilot
Repository evidence for agents before they adopt dependencies, enter codebases, compare, or merge.
Tenpace Review Routerio.github.tenpace-app/review-router
Human-authenticated setup for routing GitHub pull requests into the right Slack channel.
agentsyncio.github.jarmstrong158/agentsync
Multi-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS.
BountyVerdict Agent Decision Toolsio.github.Mimirs402/bountyverdict
Free selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.
DepFeeddev.depfeed/depfeed
Change intelligence for coding agents: sourced breaking changes for npm, PyPI, and Rust packages.
Tenpace Review Routerio.github.Patrax/review-router
Human-authenticated setup for routing GitHub pull requests into the right Slack channel.
Inspectrumio.github.yannmenec/inspectrum
Review coding-agent plans on demand with peer models, attributed findings, and a structured verdict.
memiio.github.sarveshsea/memi
Memi is the read-only design engineering audit and skill layer for coding agents.
Verificate MCPai.verificate/mcp
Agentic code review, no signup to try: reality gates + frontier-model review, with veto.
Codehelperio.github.VeyrForge/codehelper
Local-first code intelligence MCP: symbol graph, impact analysis, 60+ tools.
Leporis WhatsAppio.github.admin-rstechie/leporis-mcp
Send and read WhatsApp messages on your Leporis account from AI coding agents, via your own API key.
PkgSeek Linux Intelligenceio.github.yeagoo/pkgseek
Linux package, file, command, vulnerability, lifecycle, migration, and repository intelligence.
Fuseio.github.Litenova-Solutions/fuse
Local .NET compiler verification, change impact, and typed wiring for AI agents.
Before Users Doio.github.bhuman-ai/beforeusersdo
Browser-backed QA with evidence and fix-ready reports for coding agents.
theabbieio.github.theabbie/theabbie
Live info about theabbie (Abhishek Chaudhary) from theabbie.github.io/about.json
Weavatrix Gitio.github.sergii-ziborov/weavatrix-git
Fast, bounded, read-only Git evidence for local AI coding agents.
RepoContextio.github.shmindmaster/repocontext
Read-only, commit-pinned repository context for coding agents.
seekrit — secrets for agentsdev.seekrit/remote-mcp
Encrypted store for API keys and database URLs your code needs. Use them without reading them.
Agent Nexusgithub.com/dugubuyan/agent-nexus
Document exchange for coding agents across services: versioned Markdown store, pub-sub notifications with structured diffs and lifecycle stage tracking.
MCP Linux Toolsgithub.com/gerard-kanters/mcp-linux-tools
Administer a Linux server: read files and logs, manage systemd services and cron jobs, run read-only MySQL queries, WP-CLI, Git and sandboxed Python.
StructForgeapp.askqa/structforge
Turn messy text into strict JSON schemas agents can trust (invoice, receipt, contact, resume).
TridentChain Securityio.github.DevInder1/tridentchain-security
Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload.
Forge Engineapp.forgeengine/forge
Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.
LeakRank Guardio.github.ProtoTeemo/leakrank-guard
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Unwrittenio.github.Byggarepop/unwritten
Catches files and C# members you forgot to change, learned from your repo's git history
pkgxrayio.github.adamsjack711-ux/pkgxray
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
GitHub PR Contextio.github.paarths-collab/github-pr-context-mcp
Retrieves GitHub PR history as context material; the connected IDE agent does the reasoning.
Longport MCPgithub.com/longportapp/longport-mcp
Real-time stock market data, analysis and trading via the LongPort OpenAPI.
Binkyio.github.andreisilva1/binky
Isolated dev environments, one per git worktree: ports, env, and DB slices as agent tools.
Madario.github.mohanagy/madar
Authenticated local evidence paths for JavaScript and TypeScript coding agents.
Vynixin.vynix/vynix-mcp
Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.
valvsh.valv/mcp
Let coding agents query any SQL database safely. Read-only by default and scoped by your policies.
cadloop Slicerio.github.richardofortune/cadloop-slicer
Find printer profiles, check bed fit, slice to .gcode.3mf and extract the G-code.
repoctxio.github.nugehs/repoctx
Local-first code context, impact analysis, and merge-readiness verdicts for AI agents.
MagicTeXio.github.ZoeLinUTS/magictex
LaTeX editor for AI agents: live PDF preview, PDF comments that drive edits, git history
Supericonsio.github.curlymolelabs/supericons
Multilingual semantic SVG icon search with previews for AI coding agents. 20,000+ icons.
WORKS Public Verifierio.github.DYZCODE/works-public
Independent static verification for exact immutable public GitHub commits.
Throughlineio.github.devznsh/throughline
Give Claude complete understanding of your software project.
Laguardedev.futur-panda/laguarde
Self-hostable policy control plane for AI coding agents.
Font Labio.github.jmg698/font-lab
A decision surface for typography: curate font directions on your real site, ship next/font code.
Project Context Connectorio.github.devznsh/project-context-connector
Give Claude complete understanding of your software project.
Packkitio.github.DanMat/packkit-mcp
Scaffold modern npm packages, CLIs, services and apps as a native tool for AI agents.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données. Dernière synchronisation 29 oct. 2026.
Questions fréquentes
Qu’est-ce que MCP ?
Le Model Context Protocol est un standard ouvert qui permet à un assistant IA (Claude, ChatGPT, Cursor, un agent) d'appeler des outils et de lire des données externes via un « serveur ». Un serveur distant est une URL à ajouter à votre client ; un serveur local tourne sur votre ordinateur à partir d'un paquet (npm, PyPI, Docker).
Comment ajouter un serveur MCP à Claude ou Cursor ?
Ouvrez la page du serveur ici, copiez son bloc de configuration dans le fichier de réglages MCP de votre client, puis redémarrez-le. Un serveur distant n'a besoin que de l'URL ; un serveur local demande Node (npx), Python (uvx) ou Docker.
Ces serveurs sont-ils sûrs ?
N'importe qui peut publier dans le registre. Un serveur peut lire ce à quoi vous lui donnez accès et agir en votre nom : préférez ceux dont le code est public et l'éditeur reconnu, et accordez le minimum de droits.