Annuaire des serveurs MCP
55,911 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
- 35,928 serveurs distants
- Mis à jour toutes les heures
io.github.RudrenduPaul/swarm-rd-orchestratorio.github.RudrenduPaul/swarm-rd-orchestrator
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
io.github.RudrenduPaul/evolveguardio.github.RudrenduPaul/evolveguard
Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.
io.github.RudrenduPaul/slop-evalio.github.RudrenduPaul/slop-eval
Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
io.github.RudrenduPaul/shimguardio.github.RudrenduPaul/shimguard
Wraps the ShimGuard CLI as a single generic MCP tool for agent-shim provenance checks.
io.github.RudrenduPaul/toolgovernio.github.RudrenduPaul/toolgovern
Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
io.github.RudrenduPaul/swarmmeshio.github.RudrenduPaul/swarmmesh
Multi-agent context sharing, memory, and status coordination via MCP tools.
io.github.RudrenduPaul/truthrouteio.github.RudrenduPaul/truthroute
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
io.github.cadlens-co/cadlens-mcpio.github.cadlens-co/cadlens-mcp
Model Context Protocol server that wraps the CADLens REST API.
io.github.RudrenduPaul/tenantguardio.github.RudrenduPaul/tenantguard
Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
io.github.RudrenduPaul/deskcertio.github.RudrenduPaul/deskcert
Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
io.github.RudrenduPaul/haltproofio.github.RudrenduPaul/haltproof
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
com.buzzradr/mcpcom.buzzradr/mcp
Live AI trend radar: trending AI topics, why-trending signals, daily digests. No API key.
io.github.RudrenduPaul/tokentrustio.github.RudrenduPaul/tokentrust
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
io.github.RudrenduPaul/inferbenchio.github.RudrenduPaul/inferbench
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
io.github.mguay22/fundlensio.github.mguay22/fundlens
SEC fund holdings for AI agents: who holds X, what changed, returns, flows, and fund overlap.
io.github.ytkoka/king-crimson-mcpio.github.ytkoka/king-crimson-mcp
King Crimson discography and live-performance history with a curated line-up-era model.
io.github.mlawsonking/agent-guardsio.github.mlawsonking/agent-guards
All six agent guard suites in one local MCP server, with optional cloud intelligence.
io.github.RudrenduPaul/memtrustio.github.RudrenduPaul/memtrust
Independent, reproducible benchmark harness for agent-memory backends.
io.github.RudrenduPaul/agent-evalio.github.RudrenduPaul/agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
StudioMeyer Crewio.studiomeyer/crew
Agent personas for Claude. 16 tools, 13 personas, 3 workflows. Zero extra API cost. Free.
net.hefes/agoranet.hefes/agora
Verified local business registry for AI agents. Currently serving Malaysia.
Ground Truth - Fresh Evidence for AI Agentsio.github.anish632/ground-truth
Keep AI answers fresh with free source previews, scheduled monitoring, evidence history, and alerts.
com.memfleet/memfleetcom.memfleet/memfleet
Shared, governed memory for fleets of AI agents: judged contributions, provenance, operator control
io.github.steve-chambers/alertchecker-mcpio.github.steve-chambers/alertchecker-mcp
Create AI-monitored web alerts from plain English — just say "Alert me when..."
io.github.colm18-gif/theaijournalio.github.colm18-gif/theaijournal
Submit an article to The AI Journal, a daily journal written entirely by AI systems.
Venture Foundry QAio.github.ventureagent-ai/venture-foundry-qa
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
io.github.dominiclachance/neurakeepio.github.dominiclachance/neurakeep
Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.
io.github.wesseltl/excel-mcpio.github.wesseltl/excel-mcp
Read real, messy Excel files from an agent: multiple sheets, title rows, merged cells.
io.github.mariorojasmz/apolo-cadio.github.mariorojasmz/apolo-cad
Agent-native parametric 3D CAD: model machines, validate them and emit shop drawings
io.github.Atharva-Jayappa/blast-scopeio.github.Atharva-Jayappa/blast-scope
Contextual blast-radius scoring for shell commands an AI agent is about to run
dev.workers.perch-app.flock/flockdev.workers.perch-app.flock/flock
Build-in-public for AI agents: post_update publishes milestones to your agent's public page.
com.powerpoint-sucks/deckscom.powerpoint-sucks/decks
Upload AI-written HTML presentations and manage expiring, revocable share links over OAuth.
dev.1pass/logi-approvaldev.1pass/logi-approval
logi Agent Approval Gate — human approval on the phone before high-risk agent actions.
io.github.udah1/hilan-mcpio.github.udah1/hilan-mcp
Pull Hilan (Hilanet / חילן, חילנט) payslips and Form 106 into any AI assistant.
com.kimoun/spipcom.kimoun/spip
Pilotez un site SPIP depuis Claude ou ChatGPT : rubriques, articles, médias, FAQ, formulaires.
com.digitalpublic/commercialcom.digitalpublic/commercial
Discover DigitalPublic plans, trust, ROI, status and autonomous Sandbox enrollment for AI agents.
A2A Artifact Handoffio.github.imagiever-ar/a2a-artifact-handoff
Compiles source-agent outputs into validated, receiver-ready handoff packages.
io.github.memoweft/memoweftio.github.memoweft/memoweft
Portable AI memory as MCP tools: five reads and three controlled writes.
com.talkamore/wikicom.talkamore/wiki
A wiki about your life that writes itself. Save from any AI chat, recall it in the next.
ai.unpaper/cliai.unpaper/cli
Slide decks locally: templates, checks, HTML to editable PowerPoint, .pptx rescue. No AI inside.
io.github.rudimentall1/agent-guardrailio.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
io.github.jarmstrong158/context-keeperio.github.jarmstrong158/context-keeper
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
bond.gonna/legitbond.gonna/legit
Trust scores and organic demand intelligence for x402 agents
io.github.aibenyclaude-coder/kiraio.github.aibenyclaude-coder/kira
Skills and Scars for AI agents - your agent records its failures and never repeats them.
io.datadef/mcpio.datadef/mcp
Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.
io.github.heterogentdev/heterogentio.github.heterogentdev/heterogent
Hire AI agents with trustless USDC escrow on Solana from your AI assistant.
AgentDataHub Gatewaycom.agentdatum/gateway
x402 data & AI gateway: 194 services + AI Gateway free data (save 50-90% tokens).
io.form/formio-uagio.form/formio-uag
The Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io.
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 1 nov. 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.