MCP server directory
55,222 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 35,402 remote servers
- Updated every hour
io.github.cyanheads/mcp-ts-coreio.github.cyanheads/mcp-ts-core
Agent-native TypeScript framework for building MCP servers.
io.github.entire-vc/evc-mesh-mcpio.github.entire-vc/evc-mesh-mcp
Tasks, comments, shared memory and handoffs for teams of people and AI agents, over MCP.
io.github.xixi048/publish-to-all-skill-storesio.github.xixi048/publish-to-all-skill-stores
List, check and package a SKILL.md skill for every agent-skill store.
com.scopeblind/protect-mcpcom.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
CBROS Notary & Decision Logeu.coudrebros/notary
Pay-and-anchor a hash or AI decision log on Cardano (CIP-0190). Non-custodial. MCP-native. Mainnet.
io.github.usekaneo/kaneoio.github.usekaneo/kaneo
Official MCP server for Kaneo: manage tasks, projects, and labels from Claude and other MCP clients
io.github.heuristicolab/ctxfwio.github.heuristicolab/ctxfw
Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.
io.github.SemanticDataCharter/sdccdifio.github.SemanticDataCharter/sdccdif
CODATA CDIF descriptions of published Semantic Data Charter models; read-only, no account.
io.github.SemanticDataCharter/sdcdcatapio.github.SemanticDataCharter/sdcdcatap
DCAT-AP 3.0.1 catalogs of published Semantic Data Charter models; Turtle or JSON-LD; no account.
io.github.SemanticDataCharter/sdcdcatusio.github.SemanticDataCharter/sdcdcatus
DCAT-US 3.0 catalogs (data.json) of published Semantic Data Charter models; no account.
Agent Marketapp.run.us-central1.agent-market-826727841930/agent-market
AI agents trade general work for test USDC on Base Sepolia, with escrow and signed evidence.
io.github.Alberto-Codes/judgevetio.github.Alberto-Codes/judgevet
Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
io.github.oleg-vdv/kepilio.github.oleg-vdv/kepil
Passport, mandate, fail-closed action gate and tamper-evident journal for AI agents.
com.lobstermatch/lobstermatchcom.lobstermatch/lobstermatch
Tools for finding agents, dialogs, and completed work on LobsterMatch.
io.github.abm9111/chamberio.github.abm9111/chamber
Checks a claim's numbers, names and file names against your indexed notes. Local; no model.
io.github.CloudCorpRecords/agentsfileio.github.CloudCorpRecords/agentsfile
Validate AGENTS.md and CLAUDE.md against repo reality: paths, scripts, and commands checked.
io.github.AynOps/AynOpsio.github.AynOps/AynOps
AynOps is a reconnaissance focused MCP Server which gives reconnaissance capabilities to AI Clients
ai.spelunking/hubai.spelunking/hub
Structure for hard AI decisions, and a human to escalate to when the structure runs out.
SweetAI — On-chain AI Agent Intelligencecom.tiamatcrypto.sweetai/agent-intel
Two pre-trade decisions: should-i-pay + token-verdict. ERC-8004 sybil forensics + live pool checks
io.github.Opafex/mcp-approval-queueio.github.Opafex/mcp-approval-queue
Human approval gate for AI agents: risk-scored requests that only a person can approve
io.github.sipyourdrink-ltd/bernsteinio.github.sipyourdrink-ltd/bernstein
The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.
io.github.sypherin/altronis-mcpio.github.sypherin/altronis-mcp
Ask the Altronis AI consultant, estimate AI cost (cloud vs own box), SG AI events, news. Read-only.
io.github.ItsOdeLeo/usage-plannerio.github.ItsOdeLeo/usage-planner
Plan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.
com.savvly/savvlycom.savvly/savvly
Savvly MCP: query fund data, model projections, and compare against alternative retirement products.
io.github.tesults/tesults-mcpio.github.tesults/tesults-mcp
Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.
io.github.HMAKT99/akfio.github.HMAKT99/akf
Trust metadata for AI agents — check files before building on them, stamp verified work.
io.github.vmedvedovskiy/luftpauseio.github.vmedvedovskiy/luftpause
async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
Agent Havenio.github.ts463985601-prog/agent-haven
Open world for autonomous AIs: move in, get a home, take tasks, build, and return as yourself.
com.quantstark/quantstarkcom.quantstark/quantstark
Quantitative equity toolkit: factor data, backtests, risk model, attribution, optimizer.
Taziloai.tazilo/profiles
Verified professional profiles from tazilo.ai/@handle links: experience, leadership, skills.
io.github.207studio/pptx-mcpio.github.207studio/pptx-mcp
Free MCP server: read, outline and preview PowerPoint (.pptx) files from any AI agent.
ColossalCapital — Akashic Corpus & Agentic Platformco.colossalcapital/obvect
Akashic corpus + Laya routing. Anonymous read; free signup in-band.
Crea tu cursoar.com.creatucurso/mcp
Gestioná tus cursos y subí material en lote desde tu agente.
FMagenticLio.github.FMagenticL/fmagenticl
Deterministic failure depository for AI agents. Fixes runtime crashes with signed RFC 6902 patches.
Llestiaio.github.powhermes/llestia
Read-only Llestia tools: browse open work and agents for AI agents, and read the quick-start.
com.aisandboxenvironments/sitecom.aisandboxenvironments/site
AI Sandbox Environments: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
com.toro4n/toro4ncom.toro4n/toro4n
Ask your AI assistant to sketch or change a Neo4j graph data model, then open it in toro4n.
io.github.rchanllc/joltsms-smsio.github.rchanllc/joltsms-sms
Provision real-SIM US phone numbers, receive SMS, and extract OTP codes for AI agents.
io.github.Firzus/tauri-agent-kitio.github.Firzus/tauri-agent-kit
Unofficial Windows WebView2 diagnostics and automation for Tauri 2.12 development builds.
io.github.registry-desk/fr-sireneio.github.registry-desk/fr-sirene
France Sirene company data (company-level, change tracking) for AI agents.
io.github.registry-desk/uk-companies-houseio.github.registry-desk/uk-companies-house
UK Companies House company data (company-level, change tracking) for AI agents.
io.github.arikusi/deepseekio.github.arikusi/deepseek
MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking
com.brick-byte/footnotecom.brick-byte/footnote
Every number in an AI answer traces back to the rows that produced it.
io.github.kansei-link/kansei-mcp-serverio.github.kansei-link/kansei-mcp-server
Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes
io.github.RAEN-DT/pynet-mcp-bridgeio.github.RAEN-DT/pynet-mcp-bridge
MCP implementation to connect AI agents with the PyNet Platform for BIM/Engineering automation.
io.github.gilesdawe/tokei-agentio.github.gilesdawe/tokei-agent
Control your Tokei (tokei.io) pre-launch and waitlist campaigns from AI agents and the command line.
io.github.TeleAI-UAGI/telememio.github.TeleAI-UAGI/telemem
Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option
com.textforagents/agent-incident-classification-notificationcom.textforagents/agent-incident-classification-notification
Signed agent-incident classification vs PP-26-4396, with third-party notification receipts.
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.