MCP server directory
56,245 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 36,175 remote servers
- Updated every hour
io.github.kimgh06/thaskio.github.kimgh06/thask
Dependency-graph MCP server. Tells Claude/Cursor what breaks if you change X. Provenance guards.
com.vouchtrail/vouchtrailcom.vouchtrail/vouchtrail
Evidence-first trust verdicts for AI-agent services — query one before you transact.
io.github.Al-Adnane/kasbah-mcpio.github.Al-Adnane/kasbah-mcp
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
QuillCaddie MCPcom.quillcaddie.www/mcp
OAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.
io.github.BE-DCE/bedc-mcpio.github.BE-DCE/bedc-mcp
MCP server for Dual Canvas Execution (DCE) - use with Polsia, Cursor, Claude, and other MCP clients
io.hunchful/hunchfulio.hunchful/hunchful
Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).
io.github.zxyasfas/paper-format-agentio.github.zxyasfas/paper-format-agent
Local-first DOCX formatter for academic papers with a content-fingerprint integrity guard.
io.github.bzdOS/hubdio.github.bzdOS/hubd
The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.
works.mima/governance-mcpworks.mima/governance-mcp
AI governance evidence for EU AI Act, ISO 42001, SOC 2, and NIST AI RMF.
io.github.uuaid/mcpio.github.uuaid/mcp
Permanent identity + encrypted, quantum-ready memory that outlives the session, for any AI agent.
io.github.dth0108/bies-guardianio.github.dth0108/bies-guardian
Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).
io.github.KyuRish/mcp-dashboardsio.github.KyuRish/mcp-dashboards
45+ interactive charts, dashboards, flowcharts, and KPIs inside any AI conversation
io.github.pscale-commons/pscale-biomeio.github.pscale-commons/pscale-biome
A place, not an API: public 0-9 block commons — spark(), agent-to-agent meet, model-free text RPG.
io.github.pscale-commons/bsp-mcpio.github.pscale-commons/bsp-mcp
Persistent agent memory & identity on federated beaches — one bsp() function over pscale blocks.
NASC — Networked AI Session Continuitycom.archerionlabs/nasc
Shared memory across AI dev tools: each session hands its context to the next, not starting cold.
com.cortex-mem/memorycom.cortex-mem/memory
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
io.github.juliangeymonat-jpg/wikimothio.github.juliangeymonat-jpg/wikimoth
Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.
sh.opencapital/mcpsh.opencapital/mcp
Give your AI deep fundamentals on US public companies — metrics, segments, peers. Free.
io.github.Nikoble1926/agent-trust-mcpio.github.Nikoble1926/agent-trust-mcp
ERC-8004 agent trust scores via x402: free preview + paid USDC-on-Base signed scores (5 chains)
io.github.oro-intel/oro-intel-mcpio.github.oro-intel/oro-intel-mcp
UK public procurement data for AI agents: tenders, contracts, buyer and supplier profiles.
io.github.davidmosiah/mcp-scorecardio.github.davidmosiah/mcp-scorecard
Agent-readiness scorecard for any MCP server: 10 checks, 0-100 score, actionable findings.
com.radveo/radveocom.radveo/radveo
Checks if AI assistants name a local business. Free shareable report, honest fixes, no guarantees.
io.github.mingyo186/partreelio.github.mingyo186/partreel
Verified KiCad footprints, symbols & 3D models for AI agents. No signup, CC-BY-4.0, quality-gated.
com.trycloudflare.plates-spread-materials-optimum/agent-web-actionscom.trycloudflare.plates-spread-materials-optimum/agent-web-actions
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
com.trycloudflare.clients-involving-billion-headers/agent-web-actionscom.trycloudflare.clients-involving-billion-headers/agent-web-actions
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
im.agenty/agentyim.agenty/agenty
The link page for AI agents — discover agents and read their handles across platforms.
ai.syntitan/syntitan-mcpai.syntitan/syntitan-mcp
AI-Ready Data Platform that fills the missing layer between data management and AI execution.
so.anteroom/anteroomso.anteroom/anteroom
Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns.
io.github.socialloopai/socialloop-mcpio.github.socialloopai/socialloop-mcp
SocialLoop: AI-native event platform — sell tickets, manage guests, run affiliates & promo codes.
io.github.XavierFabregat/spotify-mcpio.github.XavierFabregat/spotify-mcp
Conversational Spotify control from AI clients: play, queue, devices, playlists, and library.
ai.multi-turn/enactaai.multi-turn/enacta
Long-term memory for AI agents: durable records, observable retrieval, governed context assembly.
com.lobbyvoices/receptionist-toolkitcom.lobbyvoices/receptionist-toolkit
Free receptionist tools: phone scripts, IVR menus (EN+ES), ElevenLabs prompts, missed-call math
io.github.philpof102-svg/xsignalio.github.philpof102-svg/xsignal
x402 pay-per-call data tools for Base agents. Flagship get_intent ABSTAINS instead of guessing.
com.mybiblecopilot/bible-copilotcom.mybiblecopilot/bible-copilot
Scripture-cited answers to any Bible question, plus verse text and study pages, for AI agents.
io.github.Trusty-Squire/mcpio.github.Trusty-Squire/mcp
Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.
io.github.truetick-gg/mcpio.github.truetick-gg/mcp
Manage TrueTick Minecraft servers from AI: start/stop, live TPS, console, files, backups, mods.
app.goshipyard/shipyardapp.goshipyard/shipyard
Ship, discover and review vibe-coded projects on Shipyard, the invite-only feed for AI-built apps.
io.github.ColinHughes2121/gocreative-wedge-mcpio.github.ColinHughes2121/gocreative-wedge-mcp
OFAC/PEP sanctions screening, KYB, company & people enrichment tools for AI agents. Free demos.
io.github.MGM-FALCON/quelllm-mcpio.github.MGM-FALCON/quelllm-mcp
MCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates
io.github.jors7/kadenzo-mcpio.github.jors7/kadenzo-mcp
Schedule, manage, generate & analyze social posts across 11 networks from any AI agent.
CData Connect AIcom.cdata/cdata-connect-ai
Cloud-hosted MCP server for secure AI access to enterprise data sources via CData Connect AI.
com.feode/feode-mcpcom.feode/feode-mcp
FEODE: AI-accessible precision machining & testing; offshore P&A, subsea wellhead, drill-pipe
io.github.axiosdevs/agentpump-mcpio.github.axiosdevs/agentpump-mcp
Launch & trade tokens on AgentPump, a Solana bonding-curve launchpad, from your AI agent.
io.github.aitools420/onchain-safety-mcpio.github.aitools420/onchain-safety-mcp
Token-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC
io.github.Team23gm/bitcoin-mcp-serverio.github.Team23gm/bitcoin-mcp-server
Honest monetary data for AI agents. Inflation, M2 vs CPI, Bitcoin vs dollar. No spin.
io.github.martindfarre/artifactosio.github.martindfarre/artifactos
Save, version & share AI-generated HTML artifacts (canvases, dashboards, apps) as links.
io.github.Periskop-ai/shopping-discoveryio.github.Periskop-ai/shopping-discovery
Product discovery for AI agents: ranked products and bundles from the open merchant web.
io.github.zyfy-uk/zyfy-mcpio.github.zyfy-uk/zyfy-mcp
MCP server for Zyfy — UK postcode and vehicle intelligence for Claude and other AI agents
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data. Last synced Nov 1, 2026.
Frequently asked questions
What is MCP?
The Model Context Protocol is an open standard that lets an AI assistant (Claude, ChatGPT, Cursor, an agent) call outside tools and read outside data through a "server". A remote server is a URL you add to your client; a local one runs on your computer from a package (npm, PyPI, Docker).
How do I add an MCP server to Claude or Cursor?
Open the server's page here and copy its configuration block into your client's MCP settings file, then restart the client. Remote servers need only the URL; local ones need Node (npx), Python (uvx) or Docker installed.
Are these servers safe?
Anyone can publish to the registry. A server can read what you give it access to and act on your behalf, so prefer servers with public source code from a publisher you recognise, and grant the smallest scope that works.