What is an MCP server?
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Discover awesome MCP servers.
AngeloBoggio
Creating an MCP server in order to plug it with a slack-bot
neddes
PieterPost MCP lets AI agents prepare, price, review, pay for, and send real letters and postcards through PieterPost.
MCP-Mirror
Mirror of
MCP-Mirror
Mirror of
adietish
numbererikson
Shinobi gives every AI coding agent on your machine — and every cloud Claude session — one shared task spine, decision log, and searched dead-ends ledger. Every failed approach is logged and semantically checked before an agent proposes a similar one, so agents stop repeating mis
dakotatores01
samehjarour
CrewAI Enterprise MCP Server Actor for Apify platform - provides AI agent orchestration via Model Context Protocol
Charlytoc
anmiralles
Quarkus example about how to create mcp server which allows to interact with our REST api through Tools definition.
TangoIndiaPapa
Model Context Protocol Server using FastMCP 2.0 to enforce policies
sairambokka
An MCP server for the open source MISP project
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Salesforce Marketing (beta): https://www.cdata.com/download/download.aspx?sku=FEZK-V&type=beta
vjgit-369
Jmeter Demo Using Jmeter MCP Server
harishakumarn
Generate smart QR codes for App Store and Google Play. One QR detects the device and redirects iOS users to the App Store and Android users to Google Play. Free, no subscriptions, no third-party servers in the redirect chain.
silentdany
Brieform is an AI-native form builder built conversation-first. Other form builders bolt an MCP server onto a dashboard designed for clicking. Brieform works the other way: connect once in your chat client's MCP settings, describe a form, get a live URL back, and read responses i
uindow
Real browser automation for AI agents. Uindow ships a local MCP server that drives a real, signed Chromium/Electron browser with genuine OS-level input (real cursor movement, real keystrokes, native file dialogs) entirely on the user's own machine.
0nilinkz
Multi-platform environment detection MCP server for VS Code Copilot integration
amcchord
MCP Server for the Slide API
omeletJK
A Model Context Protocol server for solving Traveling Salesman Problem (TSP)
jchandani
a-polishchuk
Simple MCP server implementation
popstas
superdwayne
saikrishna0716
Himalayas-App
A Model Context Protocol (MCP) server that provides access to remote job listings and company information from Himalayas.app.
Aryan-Jhaveri
A MCP Server for Canada's Food Guide - To allow LLM's with preset webscraping tools to fetch recipes.
mehmet-arikan
sympleaichat
An enhanced Conway's Game of Life simulation that runs as an MCP (Model Context Protocol) server for Claude Desktop.
schmitech
Pluggable web chat widget to interact with ORBIT MCP server.
brannn
MCP server for managing your Fly.io infrastructure
theadminautomated
oleksiijko
Local-first persistent memory for AI coding agents over MCP. Gives Claude Code, Cursor and Codex shared, durable project memory across sessions. No cloud, no API keys.
MCP-Mirror
Mirror of
tejkiran7
tzujohsu
setting up a mcp server tool to search the latest documents via Serper API
CodeHalwell
Repo to hold the code for the mcp server built in Gradio for the agents and mcp hackathon
seemueller-io
an mcp server with candle inference
Sami-07
A Simple custom-built MCP server that provides GitHub integration features through various tools and resources.
Choppaaahh
Neutral, non-custodial payment router for AI agents — pay across x402 (EVM + Solana) and MPP rails through one integration. Interline discovers which rail an endpoint accepts and settles buyer→seller directly with your own wallet key; it never holds funds.
fastnai
Unified Context Layer (UCL) is a multi-tenant Model Context Protocol (MCP) server that enables AI agents, automation platforms, and applications to connect to over 1,000 SaaS tools—such as Slack, Jira, Gmail, Shopify, Notion, and more—via a single standardized /command endpoint.
kenneth-bro
Nimistu
RicardoCenci
Simple Model Context Protocol (MCP) server for Wiki.js
scjang01
# tossinvest-mcp
michaelhologram
Synthetic data generator MCP server. Generates realistic companies, documents, and structured data — e.g. to populate SharePoint/test/demo systems. 19 tools, stdio, requires CLUTTER_API_KEY.
debitura
faizbawa
MCP server giving AI agents full SSH access with secret-safe environment variable injection. Supports persistent sessions, structured command execution, SFTP file transfer, port forwarding, and automatic output redaction that prevents secrets from reaching the LLM.
keenableai
Live web search and clean-markdown page fetch over the Keenable web index. Two tools: search_web_pages (live web search with site/date filters) and fetch_page_content (URL to clean markdown). Keyless by default (1,000 req/hour); an optional API key lifts the cap. Hosted Streamabl
Oolab-labs
A local-first MCP bridge for Claude Code, Claude Desktop, and other MCP clients. 177 tools (LSP, debugger, terminal, git, GitHub, file ops) via a companion VS Code extension, with an optional layer for YAML automation recipes, a human approval queue, persistent decision traces, a
mxxfun
# Splid MCP Server
tanranv5
PatrykIti
Modular MCP Server + Blender Addon for AI-Driven 3D Modeling.
obcraft
Official MCP server for discovering, paying for, and publishing APIs through the Apiosk gateway. AI agents can browse the API catalog, execute any listing through a uniform contract or API-specific tools, and settle paid calls automatically over USDC (x402 on Base), no manual pay
orcalayer
MCP server for Polymarket whale tracking and smart-money analytics. Filtered leaderboard (airdrop-farmers excluded), hedge detection, NegRisk correction, and unique Ukraine territorial markets with ISW frontline overlay. 5 tools, 4 prompts, 3 resources.
topiclakeinsights-crypto
An MCP server for accessing TopicLake policy insights data, including documents, topics, Q&A, sentiment, and summaries, using the Stainless SDK. Easily integrates with Claude Desktop, Abacus.AI DeepAgent, and other MCP-compatible tools.
wongcyrus
MCP server for robots
aartiq
The most comprehensive ServiceNow MCP server — 400+ tools across 35+ modules including ITSM, ITOM, CMDB, HRSD, CSM, SecOps, GRC, Flow Designer, Service Catalog, UI Builder, and Performance Analytics. Features 26 AI capabilities (scan, review, build, ops, docs), SDK mode, Direct
mukul-dutt
Track brand mentions, ranks, and citations across ChatGPT, Claude, Gemini, Perplexity, Google AI Overviews, AI Mode, and Bing Copilot. MCP-native, pay-as-you-go, $1 free signup credit.
openocean-finance
An MCP server for executing token swaps across multiple decentralized exchanges using OpenOcean's aggregation API.
Common questions about MCP servers, tools, and integrations
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Every server's detail page includes ready-to-paste config snippets for Claude Desktop, Cursor, VS Code, and other common clients — most installs take just a couple of minutes.
Most servers listed here are free and open source. Some wrap third-party APIs (cloud services, paid data providers, etc.) that require your own API key or subscription.
A local MCP server runs on your device and usually connects over stdio, giving you more direct control over data but requiring a runtime and installation. A remote MCP server is hosted by a provider and connects over HTTP, making setup easier while adding network and provider availability dependencies.
Claude Desktop, Claude Code, Cursor, VS Code, Codex, and other AI clients that support the Model Context Protocol can connect to MCP servers. Configuration formats and supported transports vary by client.
Review the source repository, maintenance activity, dependencies, requested permissions, and data-handling documentation before installation, and prefer official or trusted maintainers. Use least-privilege credentials for sensitive access such as files, databases, shells, and production systems.