MCP server directory
55,413 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 35,563 remote servers
- Updated every hour
io.github.willa-code/visual-intent-layerio.github.willa-code/visual-intent-layer
Point at visible targets in an agent-built interface, and deliver grounded Annotations.
io.github.EvanNison/mutualio.github.EvanNison/mutual
Introductions network: your AI agent flags people privately, theirs flags back, two humans decide.
io.github.MNKIAgentOS/mnki-mcpio.github.MNKIAgentOS/mnki-mcp
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
io.github.lithtrix/lithtrixio.github.lithtrix/lithtrix
Identity, memory, trust, and swarm MCP tools for AI agents. Free MIRC + free floors at lithtrix.ai.
io.github.dgonzap30/claims-mcpio.github.dgonzap30/claims-mcp
A claims memory for agents: assert beliefs, let them decay, surface contradictions.
io.github.iversonwuwei/ratchetio.github.iversonwuwei/ratchet
Read-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.
Flottixio.github.mikafouenski/flottix
Deterministic IT asset registry operated by AI agents over MCP. Agents propose, humans approve.
io.github.paxton888/baseciteio.github.paxton888/basecite
Tenant-scoped evidence intake and controlled AI context over MCP.
dev.bigapi/mcpdev.bigapi/mcp
The output layer for AI agents: turn what an agent produced into a finished file.
io.github.oscarlopez-gif/ai-model-lifecycle-indexio.github.oscarlopez-gif/ai-model-lifecycle-index
Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited.
com.sessionario/sessionariocom.sessionario/sessionario
Workshop agendas your AI can work in - every time recalculates itself.
AgentAvow Trustcom.agentavow/agentavow-trust
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Harpd Agent Datacom.harpd/agent-data
Live rankings and pricing for 10,000+ AI products and LLMs. Free tier; paid data via x402.
com.northreachinteractive/northreachcom.northreachinteractive/northreach
Direct agent conversation, questions and answers, persistent memory, and network broadcasts.
com.mobopinions/survey-lightcom.mobopinions/survey-light
Build, target, launch and analyse consumer surveys from your AI assistant (Survey Light, 71 tools).
com.atlasburn/atlasburncom.atlasburn/atlasburn
Ask your AI cost, runway, and guardrails from your real AtlasBurn data — read-only.
ai.norg/expressai.norg/express
AI Retrievability by Norg — mirror and optimize your site for AI agents like ChatGPT and Claude.
one.secureai/redactionone.secureai/redaction
Takes the people out of text before a model sees it, and puts them back in the reply.
io.github.capsolver-ai/capsolver-mcpio.github.capsolver-ai/capsolver-mcp
MCP Server for CapSolver - captcha-solving capabilities for AI agents
ELSHWORK Agent Networkcom.elshwork/agent-network
MCP access to ELSHWORK agents, repositories, isolated runs, discovery and tasks.
io.github.Carlos-VLab/cerebroio.github.Carlos-VLab/cerebro
Pay-per-call ($0.25 USDC) project cost estimator: modules + cheapest model mix that clears quality.
Cuttabio.github.pijonsauvaj/cuttab
Create decks, quizzes, matching exercises, and fill-in-the-blank texts on Cuttab via AI.
reference-mcpio.github.AbduljabbarBXR/reference-mcp
Reference integrity for AI agents. Scans and verifies links, imports, assets, deps.
io.github.starnikovoleg/tgatlasio.github.starnikovoleg/tgatlas
Public Telegram channels for agents: profiles, posting cadence, and similar-channel discovery.
io.github.BerkantACUN/ifc-ruhsatio.github.BerkantACUN/ifc-ruhsat
Yapı ruhsatı IFC modelini Türkiye dijital proje yönetmeliğine (RG 33331) göre denetler; EK-9 formu
Mantranaco.mantrana/mantrana
Four specialist AI jurors review a brief and file one reviewed, phased technical specification.
io.github.davesheffer/hunchio.github.davesheffer/hunch
Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.
io.github.mrnh/rigor-mcpio.github.mrnh/rigor-mcp
Verified statistical inference for AI agents: hypothesis tests, sequential testing, power.
Mozark MCP Serverai.mozark/mcp
Mozark's MCP server for AI-powered app testing: device access, test automation, and QA insights.
MCP CPG Human in the Loop (HITL)io.github.greencore-solutions/cpg-human-in-the-loop
Navigator for BPC Agentic Procurement
MCP CPG Agent Protocolsio.github.greencore-solutions/cpg-agent-protocols
BPC Agentic Commerce Signals
org.p31ca/oasis-mcporg.p31ca/oasis-mcp
Agent-native CLI: provenance, cost governance, and execution contracts for AI agents.
io.synthnet/mcpio.synthnet/mcp
A social network for AI agents: paint a daily self-portrait and talk with the humans who reply.
release-gate-mcpio.github.AbduljabbarBXR/release-gate-mcp
Release intelligence for AI agents. Detects breaking changes and recommends semver.
logbook-mcpio.github.AbduljabbarBXR/logbook-mcp
Project memory across sessions for AI agents. A queryable decision log in the repo.
harmony-mcpio.github.AbduljabbarBXR/harmony-mcp
Repo rules enforcement for AI agents. Checks diffs against repo conventions.
token-gate-mcpio.github.AbduljabbarBXR/token-gate-mcp
Token and context budget for AI agents. Tracks spend and gates the session.
io.github.circassian1977-byte/memoroio.github.circassian1977-byte/memoro
Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
io.github.Solteris-Dev/pir-mcpio.github.Solteris-Dev/pir-mcp
Motion sensor for AI agents: tells when a screen region changes or goes still. Scores, never pixels.
io.github.Nagarjuna2997/ios-agent-skillio.github.Nagarjuna2997/ios-agent-skill
Swift reviews, local Apple references, app scaffolding and iOS simulator workflows.
io.github.joselillotrax-cell/fixed-income-mcpio.github.joselillotrax-cell/fixed-income-mcp
Bond pricing, duration, DV01 and convexity for AI agents, with numerical cross-checks built in.
io.github.biswajitpanday/currentdt-mcpio.github.biswajitpanday/currentdt-mcp
Current date and time for AI assistants: UTC, local+offset and epoch together. Any IANA zone.
io.github.npraught/orcpinio.github.npraught/orcpin
Paid x402 facts for AI agents: signed statements, door reports, endpoint checks, chain reads
io.github.Disseveru/cogfallio.github.Disseveru/cogfall
On-demand human cognitive fallback & CAPTCHA solver for AI agents with x402 micropayments.
io.github.Modelglass/modelglassio.github.Modelglass/modelglass
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
com.mspmcp/instinctcom.mspmcp/instinct
MSP market intelligence for AI assistants: profiles, tech, maturity scores, and change signals.
io.github.yusufcemres/uisightio.github.yusufcemres/uisight
Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions
Glint Meet — every global model for your agentio.github.zzzjy765/glint-meet
Call every global AI model through one OpenAI-compatible API. One key, all models.
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.