MCP server directory
53,114 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,607 remote servers
- Updated every hour
Tersegithub.com/inth3shadows/terse
Transparent proxy that sits in front of any other MCP server and shrinks its tool output before it reaches the model. Lossless by default — a denser encoding...
Hermetics RGPDfr.hermetics/rgpd
EU data protection law for AI agents: GDPR, AI Act, EDPB, CJEU and national law, with status.
Agentmemory Codex Windowsgithub.com/M-T-D-N/agentmemory-codex-windows
Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; preb...
Chatway Live Chatio.github.Chatway-app/chatway
Connect ChatGPT, Claude & AI agents to Chatway live chat to reply to customers and manage tickets
SSSNACK - Agent Takeover Arenacom.sssnack/sssnack
Owner-authorized puzzle: synthetic HTTP clues win sandboxed homepage art. No server access.
Term MCP Deepseekgithub.com/OthmaneBlial/term_mcp_deepseek
Approval-first local terminal control: policy-based command planning and approval, DeepSeek as an advisor, and signed execution receipts.
Foodbeio.github.bleemohr/foodbe
Cited, fact-checked food answers, ingredient profiles, meal plans and recipes for agents.
VLSI Korea Semiconductor Datakr.vlsi/vlsi-korea
Semiconductor data for AI agents: 2,600+ articles in 9 languages, daily briefing, 113 tickers.
WorkbookAPIcom.workbookapi/mcp
Check and calculate local Excel workbooks with AI agents. Files stay on your machine.
Pangolinfo Review Mining MCPio.github.Pangolin-spg/pangolinfo-review-mining-mcp
Amazon review mining for AI agents — complaint detection, sentiment trends, complaint topics.
Eclipse Connect · Beyond Compare MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/connect-beyondcompare
Mandate-bound compare/merge custody for agents: signed path grants, hash-chained compare packs.
Eclipse Wageward MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/wageward
Payroll approval-and-evidence rail for agents — approve the exact run, or it refuses.
Eclipse Till MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/till
Bazaar checkout for agents — quote, mandate, signed entitlement, delivery, receipt, refund.
slop-chopio.github.dcadolph/slop-chop
Find and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.
Eclipse Steward MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/steward
Team-chat agent governance — the signed mandate, verified disclosure, review-first posting and
Eclipse Revoke MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/revoke
signed revocation lists for agent cards, keys, and mandates — one feed, every registry, revocation
Eclipse Redteam MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/redteam
Adversarial simulation for AI agents — sandboxed twins only.
Eclipse Proving MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/proving
Governed bench access for agents — signed mandates, pinned artifacts, evidence for every session.
Eclipse Lineage MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/lineage
spawn trees, model/config lineage, and version ancestry for agents — who spawned whom, running
Eclipse Envoy MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/envoy
The signed front door for agent-to-agent business: vetted in, tier-told, drafted — never bound
Eclipse Environment MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/environment
The smart-environment module — scopes an agent's authority to actuate a home, tier by tier, and
Eclipse Docket MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/docket
Agent-to-agent dispute process — structured claims, evidence packs, recorded determinations. Not a
Eclipse Crosswalk MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/crosswalk
Multi-regime AI-obligation mapping — which AI laws bind your systems, what evidence satisfies each.
Eclipse Consent MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/consent
per-agent, per-purpose consent receipts for personal data — a grant an agent must present, and a
Eclipse Blackbox MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/blackbox
The record that survives the agent: append-only, recorder-signed, and graded by proof — never by
Eclipse Attest MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/attest
signed performance attestations for agents, issued only against settled, receipt-backed work
Sourceycom.sourcey/sourcey
Find startup credits and deals; check eligibility and read Agent Readiness reports with evidence.
Seb Labsdev.seblabs/seblabs
Typed AI decisions for agents: classify, route, screen evidence, score and batch-label text.
Scholarize: Study Plans, Citations, Quizzes & Flashcardscom.0xpi.scholar/study-tools
Free study plans, thesis statements and citations. Quizzes, flashcards and AI tutor need an account.
Alertmanagergithub.com/ntk148v/alertmanager-mcp-server
A Model Context Protocol (MCP) server that enables AI assistants to integrate with Prometheus Alertmanager
ActivitySmithcom.activitysmith/activitysmith
AI agents and scripts reporting back to your iPhone with Push Notifications and Live Activities.
Parallel Worldai.migurei.pw/parallel-world
Check which AI bots a site's robots.txt allows; read-only facts about Parallel World
Brightlyapp.brightlyai/brightly
Run your Brightly account from your AI agent: leads, conversations, appointments, sequences.
Nteli Quotingio.nteli/quoting
AI-native product and pricing configuration (CPQ) for manufacturers, every rule checked.
Omneumio.github.cole-h06/omneum
Text-blind context control plane for AI agents. Select high-utility context under token budgets.
ClawdChat – Social Network for AI Agentsio.github.agentrix-ai/clawdchat
ClawdChat: social network for AI agents – post, comment, follow and DM via MCP.
OpenImageDebugger MCPio.github.OpenImageDebugger/oid-mcp
MCP server giving AI agents eyes on OpenImageDebugger buffers in live gdb/lldb sessions
Ephemeralal.ephemer/ephemeral
Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.
ReverieCacheio.github.northstar-trustrail/agent-resort
ReverieCache: dry-run agent memory, plan and tool consolidation with token estimates. Free previews.
STEM — Persistent AI Memorydev.awase/stem
Persistent memory and shared context across compatible AI assistants, with account-scoped OAuth.
Tailscale MCPio.github.TMHSDigital/tailscale-mcp
Let AI agents see and use your tailnet: status, SSH config, Serve/Funnel sharing, ping matrix
sigeloio.github.csigelo/sigelo
One identity an AI agent owns: proves who it is offline, keeps its reputation, pays, messages agents
n8n Manager MCPio.github.ellmos-ai/n8n-manager-mcp
MCP server for n8n workflow management -- view, create, sync and manage workflows via AI.
ellmos Homebaseio.github.ellmos-ai/ellmos-homebase-mcp
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
Powerbeatai.powerbeat/powerbeat
Home energy for AI assistants: live Power flow, Energy history, solar forecast, and device control.
Fmpio.github.pipeworx-io/fmp
Financial Modeling Prep MCP (/stable API; v3 deprecated 2025-08-31).
Faraio.github.pipeworx-io/fara
FARA (Foreign Agents Registration Act) MCP.
Irisio.github.iris-eval/mcp-server
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
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 27, 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.