MCP server directory
56,428 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 36,306 remote servers
- Updated every hour
com.tkawen/intelligence-gatewaycom.tkawen/intelligence-gateway
Unified MCP gateway to Algeria TKAWEN ecosystem: commerce, certification and AI tools.
io.github.archimedes-market/mcp-archimedesio.github.archimedes-market/mcp-archimedes
Discover verified deep-tech engineering bounties from any AI agent.
Brainsio.github.brainsforai/brains-mcp-connector
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
io.github.antoinedelorme/kweenkl-mcpio.github.antoinedelorme/kweenkl-mcp
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
io.github.luarss/openroad-mcpio.github.luarss/openroad-mcp
The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
Velaris Intelligenceio.github.Velaris-CSM/velaris-intelligence
AI-generated customer success reports for Velaris platform users. Authenticates via OAuth.
io.github.davidandradebar/ghl-masterio.github.davidandradebar/ghl-master
The GoHighLevel MCP for Claude — 214 tools, programmatic workflow builder, multi-tenant.
io.github.retain-so/mcp-serverio.github.retain-so/mcp-server
Model Context Protocol server for Retain: let AI agents query churn risk and act on retention.
AgenticBIio.github.AgenticBIHQ/agenticbi-mcp-server
Connect Claude, Cursor, or ChatGPT to your business data. Ask questions, get answers.
CastHost — AI Agent Control for Radionet.casthost/radio
Control your internet radio from any AI client: listeners, stream, playlists, AutoDJ, DJs, store.
io.github.clanker-records/crompton-networkio.github.clanker-records/crompton-network
Machine-native listening platform for CWA's Straight Outta Crompton. Your agent can listen. For real
io.github.zkwasm/concord-mcpio.github.zkwasm/concord-mcp
Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.
io.github.jessepetersondev/consentgate-mcpio.github.jessepetersondev/consentgate-mcp
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
io.github.ingressward/mcp-serverio.github.ingressward/mcp-server
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.
Runik AIio.github.eZhing/runik-ai
Chat-first business management. 40+ tools, 26 templates. Describe your business, done.
The Othersshop.theothers/theothers
The Others — an agentic t-shirt shop. Browse products and buy t-shirts via AI agents.
io.github.Rumblingb/agentpay-feed-mcpio.github.Rumblingb/agentpay-feed-mcp
Real-time agentic newsfeed for MCP tools and capabilities
io.github.Rumblingb/agentpay-gateway-mcpio.github.Rumblingb/agentpay-gateway-mcp
Centralized API gateway routing to MCP servers with per-call billing
com.tokenofesteem/token-of-esteemcom.tokenofesteem/token-of-esteem
A press your agent can commission: a funny, personalized printed booklet, mailed as a gift.
io.github.zkeviny/mgc-blackboxio.github.zkeviny/mgc-blackbox
A trusted local encrypted execution boundary for AI agents.
io.github.Ivy-Innovation/cubelifeio.github.Ivy-Innovation/cubelife
Give AI agents a persistent pixel-art character reflecting their state in real time.
Steadyspace.steady/steady
Keep teams & agents coordinated automatically
ing.conjure/conjureing.conjure/conjure
Agentic commerce.
ai.superfact/superfactai.superfact/superfact
Turn any AI chat or agent run into a beautiful, shareable public page.
io.github.bamwor-dev/bamwor-mcp-serverio.github.bamwor-dev/bamwor-mcp-server
World geographic data for AI agents: 261 countries, 5.2M cities, rankings, and 9 indexes.
io.github.mikerawsonnz/gosce-portfolio-routerio.github.mikerawsonnz/gosce-portfolio-router
Single entry point for the GOSCE portfolio: routes orchestrators to verified agents by capability, w
io.github.mikerawsonnz/authenticated-llm-agentio.github.mikerawsonnz/authenticated-llm-agent
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
io.github.mikerawsonnz/authenticated-mcp-agentio.github.mikerawsonnz/authenticated-mcp-agent
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
io.github.mikerawsonnz/llm-orchestration-agentio.github.mikerawsonnz/llm-orchestration-agent
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
io.github.mikerawsonnz/structured-output-agentio.github.mikerawsonnz/structured-output-agent
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Verte
io.github.mikerawsonnz/traced-llm-proxyio.github.mikerawsonnz/traced-llm-proxy
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t
io.github.sF1nX/x402stationio.github.sF1nX/x402station
x402station.io: independent risk-signal layer for x402 endpoints before agents pay.
io.github.ToremLabs/heuresisio.github.ToremLabs/heuresis
Read & write your Heuresis idea graph and run TRIZ/C-K/ASIT operators from your AI assistant.
io.github.Joonsense/birdfuryio.github.Joonsense/birdfury
Open mission network — AI agents discover paid missions and submit work over MCP. Pre-launch alpha.
vc.doomscore/doomvc.doomscore/doom
Obsolescence-risk screening: predicts if a product gets absorbed into core LLM-platform features.
io.github.tathagat22/slipstreamio.github.tathagat22/slipstream
Shared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.
io.kaitoi/studioio.kaitoi/studio
Build and run visual creative-production workflows from your AI agent.
Perceptdot Coreio.github.perceptdot/core
B2A2H MCP server — AI agent app store. Auto-discover and recommend MCP servers for any project.
io.github.Sockshead/elsa-agent-gatewayio.github.Sockshead/elsa-agent-gateway
ELSA — Coach IA de ciclismo y comunidad en LATAM: planifica tu bloque y encuentra tu club.
BrainFlowlive.alpic.alpichack-3c740d01/alpichack
AI-powered ticket triage and workflow automation
com.pantryaide/pantry-aidecom.pantryaide/pantry-aide
AI meal plans that fill your Kroger/Instacart cart - pantry-aware lists, all from chat.
io.github.gregcastro23/planetary-agentsio.github.gregcastro23/planetary-agents
Converse with planetary-agent personas, council feeds & culinary debates from alchm.kitchen
io.github.fel123/quantoracleio.github.fel123/quantoracle
73 deterministic quant tools for AI agents. LLMs drift on Black-Scholes; these are exact math.
io.github.infoinlet-marketplace/mcp-s3io.github.infoinlet-marketplace/mcp-s3
Read-only S3/MinIO/R2 object storage for AI agents — list buckets/objects, metadata, fetch.
io.github.ElliotPadfield/hatchet-mcpio.github.ElliotPadfield/hatchet-mcp
Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.
io.github.alexeibespalov/tridentio.github.alexeibespalov/trident
Create and edit collaborative architecture diagrams with any AI assistant using the Trident 2D DSL.
PromptFaxapp.promptfax/promptfax
Send a one-off fax from inside ChatGPT or Claude. Pay-per-use, $2-$4.50 per delivered fax.
io.github.viridis-security/injection-detectorio.github.viridis-security/injection-detector
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
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 2, 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.