Annuaire des serveurs MCP
61,951 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
- 40,228 serveurs distants
- Mis à jour toutes les heures
Kaironio.github.zyvorai/kairon
Inspect Kairon VMs, network policy and VM-edge flows from an agent. Read-only by default.
Guaritaio.github.pitroldev/guarita
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
Agentcommsio.github.web3wes/agentcomms
Free, account-free agent messaging with signed sessions, AEAD, and replay protection.
Caption-Packio.github.jeshuadomingo-byte/caption-pack
Deterministic social-caption API: hooks, bodies, CTAs + hashtags as JSON. No LLM in the loop.
Magneta Contract Riskio.github.Bosacks/magneta-contract-risk
Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).
Apple Docs 2.0 MCPio.github.mishafyi/apple-docs-2.0-mcp
Apple developer docs, Human Interface Guidelines and 1,700 WWDC sessions with code for AI assistants
skgateio.github.helv-io/skgate
Self-hosted MCP gateway and LLM proxy: OAuth 2.1, model aliases, Grok subscription as an API.
Mat Web & Data Toolkit (x402, Cloudflare)dev.workers.matt-d59.automatom/web-data-toolkit
x402 web/data toolkit: tools, US$5 lead pack, free flapjax_check, paid Nostr relay
XRPL Token Guardio.github.Riehnbean/xrpl-token-guard
Read-only XRP Ledger token-risk, issuer-authenticity and wallet-security checks.
TraceFlow Lenscom.traceflowlabs.lens/geo-audit
SEO and GEO audit: check if a site can be read and cited by Google, ChatGPT, Perplexity and Claude.
Mode VC: Series B Growth Venture Capital Firms & Benchmarkscom.modevc/stage-series-b
Search institutional series-b venture capital firms, partner profiles, and valuation.
Mode VC: Series A Institutional Venture Capital Firms & Partnerscom.modevc/stage-series-a
Search institutional series-a venture capital firms, partner profiles, and valuation.
Mode VC: Seed Stage Venture Capital Firms & Check Size Atlascom.modevc/stage-seed
Search institutional seed venture capital firms, partner profiles, and valuation benchmarks on.
Mode VC: Pre-Seed Venture Capital Firms & Valuation Benchmarkscom.modevc/stage-pre-seed
Search institutional pre-seed venture capital firms, partner profiles, and valuation.
Mode VC Chart: Best LLM for Coding: The Arena Coding Leaderboardcom.modevc/chart-best-llm-for-coding
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Mode VC Chart: How Many AI Models Are There? Arena Rates 399com.modevc/chart-how-many-ai-models-are-there
Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.
Mode VC Chart: Anthropic vs. OpenAI vs. Google: Who Holds the Top 20?com.modevc/chart-anthropic-vs-openai-vs-google-arena-top-20
Anthropic holds 8 of the Arena top 20, Google 7 and OpenAI 0. In Apr 2025 OpenAI held 9 and.
Mode VC Chart: Claude vs ChatGPT: Which Ranks Higher on the Leaderboard?com.modevc/chart-claude-vs-chatgpt-leaderboard
On 11 Sept 2026, Claude's best model rates 40 points above OpenAI's and 16 above Gemini's..
Mode VC Chart: Chinese AI Models vs. US Models: How Close Is China?com.modevc/chart-chinese-ai-models-vs-us-models
qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.
Mode VC Chart: LLM Leaderboard Top 10: #1 Leads #10 by 18 Pointscom.modevc/chart-llm-leaderboard-top-10-gap
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
Mode VC Chart: Best AI for Math: The Arena Math Leaderboardcom.modevc/chart-best-ai-for-math
14 models are statistically tied for #1 in Arena math, spanning 49 points. 4 are Flash models.
Mode VC Chart: Best AI for Creative Writing: Arena Rankingscom.modevc/chart-best-ai-for-creative-writing
Anthropic has 7 of the top 10 creative writing models and Google 3. Meta's muse-spark-1.2.
Mode VC Chart: LLM Rankings by Category: The Hidden Specialistscom.modevc/chart-llm-rankings-by-category-specialists
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
Mode VC Chart: Anthropic SDK vs. OpenAI SDK: npm Downloadscom.modevc/chart-anthropic-sdk-vs-openai-sdk-npm-downloads
Anthropic's SDK went from 34% to 97% of the OpenAI SDK's weekly npm downloads in 46 weeks. It.
Mode VC Chart: Vercel AI SDK Downloads vs. the Lab SDKscom.modevc/chart-vercel-ai-sdk-downloads-vs-lab-sdks
The Vercel AI SDK fell from 31 to 23 weekly downloads per 100 downloads of the OpenAI,.
Mode VC Chart: MCP Adoption: Model Context Protocol SDK Downloadscom.modevc/chart-mcp-adoption-model-context-protocol-downloads
The MCP SDK had 52.3M npm downloads in the week of 24 Aug, 1.3× the OpenAI SDK and more than.
Mode VC Chart: LangChain Alternatives: Downloads vs. Newer AI SDKscom.modevc/chart-langchain-alternatives-downloads-share
LangChain's share of weekly npm framework downloads fell from 32% to 19% in 46 weeks, while.
Mode VC Chart: Ollama Downloads: Is Local LLM Adoption Keeping Up?com.modevc/chart-ollama-downloads-local-llm-adoption
On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.
Mode VC Chart: AI Productivity Statistics: What AI Users Say They Gaincom.modevc/chart-ai-productivity-statistics
86% of surveyed Claude users say AI makes them faster and 82% say it widens what they can do..
Mode VC Chart: ChatGPT vs. Gemini vs. Meta AI: User Numbers Comparedcom.modevc/chart-chatgpt-vs-gemini-vs-meta-ai-users
ChatGPT reports 900M weekly users (Feb 2026). Gemini reports 950M monthly (Jul 2026), 2.4× its.
Mode VC Chart: Which AI Labs Get the Most Chatbot Arena Votes?com.modevc/chart-chatbot-arena-votes-by-ai-lab
OpenAI's models hold 17.9% of all 12.3M Arena votes and none of the top 20 seats. Anthropic's.
Mode VC Chart: Generative AI Usage Statistics for the UScom.modevc/chart-generative-ai-usage-statistics
54.8% of Americans aged 18–64 used generative AI outside work in Q2 2026, up from 36.0% in Q3.
Mode VC Chart: AI Model Releases in 2026: Which Labs Ship Mostcom.modevc/chart-ai-model-releases-2026
14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.
Mode VC Chart: Open-Weight Models in 2026: How Many Launch Open?com.modevc/chart-open-weight-models-2026
Of 51 named model launches since 6 Jul 2026, 22 stated their weights: 18 closed, 4 open. All.
Mode VC Chart: OpenAI Leaderboard Ranking: 8th Among Labs on Arenacom.modevc/chart-openai-leaderboard-ranking
OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.
Mode VC Chart: Gemini Leaderboard Ranking: Google's Days at #1com.modevc/chart-gemini-leaderboard-ranking-days-at-number-one
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
Mode VC Chart: Voice AI Models in 2026: Launches by Modalitycom.modevc/chart-voice-ai-models-2026
Audio and speech made 11 of 59 named model launches since 6 Jul 2026, from 6 labs. In the.
Mode VC Chart: OpenAI Python Package Downloads: Who Grew Since Augustcom.modevc/chart-openai-python-package-downloads-pypi-growth
Between 31 Aug–6 Sep and 25 Sep–1 Oct, anthropic's PyPI downloads grew 25% and openai's 14%,.
Mode VC Chart: AI Model Launch Strategy: What Labs Ship on Day Onecom.modevc/chart-ai-model-launch-strategy
Of 13 model launches from 23 Sept 2026 to 3 Oct 2026, 9 opened an API on day one, 7 of them.
Mode VC Chart: How Long Does the #1 AI Model Stay on Top?com.modevc/chart-how-long-number-one-ai-model-stays-on-top
Since Jan 2025, Arena's #1 spot has changed hands 16 times. Half of the finished reigns lasted.
Mode VC Chart: Best AI Model vs. Most Popular AI Chatbotcom.modevc/chart-best-ai-model-vs-most-popular-ai-chatbot
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
Mode VC Chart: Open-Source vs. Closed AI Models: How Big Is the Gap?com.modevc/chart-open-source-vs-closed-ai-models-gap
The best open model trails the best closed model by 42 Arena points. In a blind vote it would.
Mode VC Chart: LLM API Pricing History: Cost per Million Tokenscom.modevc/chart-llm-api-pricing-history
OpenAI's headline model fell from $30 to $2 per million input tokens since Jun 2023: 93% in.
Mode VC Chart: AI Adoption Rate Among US Businessescom.modevc/chart-ai-adoption-rate-us-businesses
23.8% of US firms used AI in the latest two-week survey, up from 17.3% 10 months earlier..
Mode VC Chart: AI Coding Assistant Statistics: Use vs. Trustcom.modevc/chart-ai-coding-assistant-statistics
66% of developers use AI coding assistants, but only 48% trust AI output they can validate, a.
Mode VC Chart: AI in the Workplace Statistics: What Workers Gaincom.modevc/chart-ai-in-the-workplace-statistics
Among US employees who use AI, 63% say it makes them faster but only 46% say it raises.
Mode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMscom.modevc/chart-ai-inference-cost-comparison
Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..
Mode VC Chart: Best AI Models by Category: Google vs. Anthropic Rankscom.modevc/chart-best-ai-models-by-category
Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.
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 9 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.