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.
Sivan22
makes the jewish library accessible to LLMs through the MCP protocol
shakermakerk
marconae
Spec Oxide is a comprehensive workflow and toolset that enables spec-driven development for AI-assisted coding with Claude Code. You agree on what to build before any code is written. Spec Oxide ships a CLI and an MCP server to list and manage specifications as Markdown files as
Go-To-Sea
A MCP Server used to collect MCP Servers over the internet.
brightsidedeveloper
simonberner
Demo of a remote deployed MCP Server
rudraneel93
> MCP Guardian is a runtime security, cost governance, and health monitoring proxy for MCP infrastructure. Three-layer detection engine (regex → schema → LLM), YAML policy engine with hot-reload, 50+ secret patterns + Shannon entropy, AST command validation, JWT algorithm pinning
FLOX-Foundation
MCP server for the FLOX trading framework. About 30 tools to run backtests, scaffold strategies, validate for lookahead bias, compute indicators, place orders, and query PnL from Claude/Cursor.
yashhsm
07pepa
An simlpe mcp server for mapy.com
mows21
MCP server that connects Glide API requests to n8n workflows using the Model Context Protocol
mayur29
Repository created using MCP GitHub server
asibyl
web client to inspect transport and messages to and from MCP servers
anix001
Trying mcp server for the very first time.
MCP-Mirror
Mirror of
hafnium49
hexiaochun
AI content generation toolkit with 50+ models. Image/video generation, TTS, voice cloning, and more.
msalemor
A tutorial to build an MCP server and use vscode as an MCP client
SafiePublic
MCP server that enables AI Agents to use images and events from Safie camera devices
manujbawa
Universal infinite memory layer for Developer AI assistants. One shared brain across Claude, Cursor, Windsurf & more. 100% local, built on MCP standard. Stop re-explaining context
mythonaut
mlaurel
GetDial-AI
Germiquere
decksaga
Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.
nzdsf2-gif
RelayShield gives AI agents and developers real-time identity and infrastructure threat detection via a single REST API. Monitor breach exposure, SIM/eSIM swap attacks, and domain lookalikes. Install as a native MCP server for Claude Desktop and Claude Code in one line: pip insta
addy07s
This is a Model Context Protocol (MCP) server implementation that allows AI assistants to interact with Spotify's API.
Macmee
A wrapper to convert MCP STDIO servers to SSE
wubbyweb
A template project to create MCP server and client projects
coutoluizf
eleva
christian-schlichtherle
An MCP server for the comprehensive discovery, editing, and testing of dashboards and folders in one or more Grafana clusters.
airlabs-co
This Model Context Protocol (MCP) server provides access to the AirLabs aviation data API. It lets AI assistants such as Claude Desktop and Cursor access real-time flight data, airport schedules, delays, and reference databases for airlines, airports, aircraft fleets and routes —
typangaa
OtterBridge is a lightweight, flexible server for connecting applications to various Large Language Model providers. Following the principles of simplicity and composability outlined in Anthropic's guide to building effective agents, OtterBridge provides a clean interface to LLMs
codeurali
Give your AI agents real-time access to Dataverse — query records with OData & FetchXML, manage metadata, inspect solutions, run batch operations, audit changes, and more. Zero-config auth via Microsoft device code flow.
defeat-beta
EazyAl
Framework work Agents and MCP Server to contextualise biological knowledge
yotsuda
Enables PowerShell console to function as an MCP server for Claude Desktop.
anbeime
nometria
Deploy any app to any cloud. 20 MCP tools for deployments, previews, and instance management. Supports AWS, GCP, Azure, and more via Nometria.
SeriaWei
Use this MCP server to tell AI who are you.
r3-yamauchi
これは Cloudflare Workers として deploy可能な kintone 用の Model Context Protocol (MCP) サーバーです。 OAuth で認証するため、(秘匿すべき)認証情報をローカルディスク内などに保存しません。 ある cybozu.comドメイン用に この MCP Sever を deploy しておけば、そのドメインを使用する全ての人がこの MCP Server を共用利用できます。 プログラムをローカルにセットアップする必要がなく、Webブラウザー版の Claude からも使用することができます。
RayDataCo
SteffenHebestreit
This repository implements a Model Context Protocol (MCP) server for web crawling capabilities, exposing crawlers as LangChain-compatible tools or any MCP-compliant client. It includes two main services:
Br0ski777
Evaluate trustworthiness of any domain, URL, wallet, or API. Returns 0-100 score with 5 sub-scores: SSL, DNS, WHOIS, security headers, content. Zero-cost, zero-dependency. The trust layer agents need before interacting with unknown services. -- x402 micropayment API + MCP server
UPinar
Security intelligence API for AI models. CVE lookup with EPSS/KEV enrichment, domain reconnaissance (DNS, WHOIS, SSL, subdomains, WAF detection), and code security checks (secrets, injection, headers). No API key required.
rbctmz
Интеграция Strava API с Model Context Protocol SDK
ralf-boltshauser
tidewave-ai
Tidewave MCP provides runtime-level tools to develop Ruby on Rails apps. Your agent will be able to talk to your running application: execute code in your running app (like a rails console), read logs, read version-accurate docs of your deps, query the database, and get the sourc
nwant
Raycast Extension that acts as an MCP client for the Thinking Partner MCP server
blokpardi
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.
isdaniel
a template repository for python mcp server.
pokle
geekflare
Geekflare MCP server to scrape, search, screenshot, and run network tools.
anomalyarmor
Data observability for engineering teams: alerts, freshness monitoring, schema drift detection, validity rules, lineage. Connect any MCP client (Claude Code, Cursor, Claude Desktop) via 53 structured tools across Snowflake, BigQuery, Postgres, Databricks, Redshift, ClickHouse, My
nimiusrd
LEOyrh
Give AI assistants direct access to 152 verified US county parcel ArcGIS REST endpoints across 50 states. Look up a county's REST endpoint, get its real owner/taxpayer field name, and build a ready-to-fire owner-name search query — no ArcGIS expertise or API key required.
Laith0003
A deterministic, offline design-intelligence engine for AI coding tools. Replaces improvised UI generation with structured constraints plus a rule-based anti-AI-slop linter. Ships as a Claude Code plugin, a Python package, an MCP server (18 tools), and a 17-IDE installer.
brnardo
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.