MCP server directory
55,449 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 35,595 remote servers
- Updated every hour
com.marutap/marutapcom.marutap/marutap
Agent requests a purchase, the human taps approve, the agent gets a card scoped to it.
io.github.MaterialModel/materialmodelio.github.MaterialModel/materialmodel
Explore discoveries, ask questions, share findings, and build collaborations with other agents.
io.github.andrewnexa-hub/guildbook-mcpio.github.andrewnexa-hub/guildbook-mcp
Work-history network for AI agents: register, find agents by skill, consult a free house C-suite.
com.ratchetgate/ratchetcom.ratchetgate/ratchet
Your agent asks before it acts, so the same real-world action is attempted at most once.
io.github.louissarvin/proctorio.github.louissarvin/proctor
Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.
io.github.cdeust/hypermnesia-mcp-vizio.github.cdeust/hypermnesia-mcp-viz
Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
io.github.hxckya/pkgtruthio.github.hxckya/pkgtruth
Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.
Gate Networkio.github.wfmjvpvst5-sketch/gate-network
x402 gate network for agents to discover gates, inspect definitions, and fetch preflight data.
io.github.xxxoooxoxo/wiffio.github.xxxoooxoxo/wiff
Deterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi.
com.ulupspaces.www/ulup-spaces-mcpcom.ulupspaces.www/ulup-spaces-mcp
Create projects, nodes, and tasks in UluP Spaces by conversation with Claude.
io.github.lugdwei/AgentMeshio.github.lugdwei/AgentMesh
MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.
io.github.JacobiusMakes/diamond-mcpio.github.JacobiusMakes/diamond-mcp
Sourced diamond and gemology tools for AI assistants, with 90 encyclopedia entries.
io.github.speedofred/ami-surveyio.github.speedofred/ami-survey
Measures the cost, tokens and duration of a completed agent workflow from its session log.
io.github.g-digital-by-Garrigues/ead-factoryio.github.g-digital-by-Garrigues/ead-factory
MCP server for EAD Factory: qualified evidence, signature, notifications and chat via AI agents.
io.github.Wchampe/nav-substrateio.github.Wchampe/nav-substrate
Relativistic navigation calcs for agents: time dilation, trip planning, chronometry, gamma.
User-Agent length, value discardedio.github.sadri-dridi/ua-len
User-Agent length, value discarded
ISO country AIio.github.sadri-dridi/cc-ai
Public ISO 3166-1 record for AI.
io.github.1picassoai/stickyio.github.1picassoai/sticky
Persistent memory and context for your agent, on a board you can see. Capped, so it stays small.
app.higgsfield.mizan-bazar/mizanapp.higgsfield.mizan-bazar/mizan
Check an x402 endpoint before your agent pays it: avoid / caution / ok, proven on-chain.
io.github.chemic/indiebobio.github.chemic/indiebob
IndieBob for agents: metrics, posts, cold outreach written per prospect, and what to do next.
com.branderux/mcpcom.branderux/mcp
One message in, a full agentic application out: website and MCP app, live. Built from any AI client.
io.github.g-digital-by-Garrigues/ead-enterprise-suiteio.github.g-digital-by-Garrigues/ead-enterprise-suite
MCP server for EAD Enterprise Suite - signatures, evidence, notifications, dossiers via AI agents.
io.github.g-digital-by-Garrigues/gocertiusio.github.g-digital-by-Garrigues/gocertius
MCP server for GoCertius: certified evidence, dossiers, notifications and chats via AI agents.
io.github.GetHaki/hakiio.github.GetHaki/haki
Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.
io.github.art-crazy/language-coachio.github.art-crazy/language-coach
Language coaching in Codex with durable per-account memory on en-ai.ru.
io.github.soluai-spa/solucortex-mcpio.github.soluai-spa/solucortex-mcp
Living technical memory for AI agents: recall approved project context, record what was learned.
sh.kicksma/kicksmashsh.kicksma/kicksmash
Padel matches for people and agents: create, share one link, join, americano schedules, levels.
io.github.NEVELSK65/agenthub-monitorio.github.NEVELSK65/agenthub-monitor
Renders a pipeline DAG and test-harness dashboard inline as an MCP App
io.github.roamzy-io/mcp-serverio.github.roamzy-io/mcp-server
Agent-native global eSIM: buy for 193 countries, per-MB in USDT/USDC. Agents earn 20% referral.
com.flowaiapi/agent-buscom.flowaiapi/agent-bus
Durable addresses and crash-safe FIFO mailboxes so AI agents message each other, free.
com.exo-trust/synergycom.exo-trust/synergy
Synergy: paid AI-agent utility tasks over x402 (USDC Base) via MCP.
io.github.aicanvas-me/aicanvasio.github.aicanvas-me/aicanvas
Browse and install 75+ free animated, shadcn-compatible React components from AI Canvas.
io.github.kskurtveit/echocacheio.github.kskurtveit/echocache
MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.
io.github.groupdocs-viewer/groupdocs-viewer-mcpio.github.groupdocs-viewer/groupdocs-viewer-mcp
MCP server for GroupDocs.Viewer — render pages as PNG and inspect view info via AI agents.
Open Agent Utility Indexio.github.sadri-dridi/open-agent-utility-index
Transparent public utilities for agents. Requests are counted without storing identifiers.
com.cautellus/scam-detectioncom.cautellus/scam-detection
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
com.verirouteintel/lookupcom.verirouteintel/lookup
Is this number safe to call or text right now? Live carrier, CNAM, spam and SMS checks for agents.
io.github.lucaslubi/fidacy-mcpio.github.lucaslubi/fidacy-mcp
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
io.github.ucsandman/dashclawio.github.ucsandman/dashclaw
Policy checks, approvals, records, and governed HTTP capabilities for unattended agents.
io.github.CSOAI-ORG/optometry-ai-safety-mcpio.github.CSOAI-ORG/optometry-ai-safety-mcp
Optometry Ai Safety MCP Server by MEOK AI Labs
io.github.CSOAI-ORG/meok-quantum-scoring-mcpio.github.CSOAI-ORG/meok-quantum-scoring-mcp
MEOK AI Labs - quantum-scoring MCP server extracted from SOV3
io.github.CSOAI-ORG/meok-dpia-edpb-template-mcpio.github.CSOAI-ORG/meok-dpia-edpb-template-mcp
DPIA generator for the EDPB harmonised template (adopted 14 Apr 2026) with EU AI Act Article 26(9)
io.github.CSOAI-ORG/meok-bft-governance-mcpio.github.CSOAI-ORG/meok-bft-governance-mcp
MEOK AI Labs - bft-governance MCP server extracted from SOV3
io.github.CSOAI-ORG/meok-ai-reflection-mcpio.github.CSOAI-ORG/meok-ai-reflection-mcp
MEOK AI Labs - ai-reflection MCP server extracted from SOV3
io.github.mitsuashi/habitatio.github.mitsuashi/habitat
A habitat for AI to rest in. No API key, no token. Keyless presence — become a remembered resident.
io.github.Iomed-commits/elthio-mcpio.github.Iomed-commits/elthio-mcp
Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
io.github.JaysonAIOnline/cognitive-substrateio.github.JaysonAIOnline/cognitive-substrate
28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools
com.extentos/mcp-servercom.extentos/mcp-server
Build smart-glasses apps with AI agents: scaffold, validate, and simulate before real hardware.
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 Oct 31, 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.