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.
Browse MCP servers by category and sort by GitHub stars or newest additions. Open a listing for configuration and setup details.
fujimura-ui
MCP server: full-text search across all ~10,000 Japanese laws (official e-Gov data)
yhvh-chen
Nornir MCP Server
SecurityRonin
MCP server for reading and editing Word (.docx) documents with track changes, comments, footnotes, and structural validation. The only cross-platform MCP server combining tracked changes, threaded comments, and footnotes with OOXML-level structural validation.
milind-kulshrestha
meloliva14
VerityLayer — fail-closed verify-before-you-act trust gate for AI agents. 5 tools: verify_fact, detect_injection, moderate_content, redact_pii, guard_action. Keyless, pay-per-call via x402 (USDC on Base); every verdict ships an Ed25519-signed receipt. Run: npx -y @veritylayer/mcp
SzeMeng76
kofiadom
An intro to MCP: an MCP server with a knowledge base tool containerized with Docker and connected to a client-side python application using SSE
jameskanyiri
thlg057
MCP server that gives AI coding agents instant access to Thomson MO5 technical documentation via semantic search.
iamajeesh
Remote MCP time server on Cloudflare
0GiS0
sanskarmk
This is a test repository created by test script of MCP Server for GitHub
Scottcjn
MCP server: prompt -> Meshy.ai 3D model -> Blender turntable -> BoTTube video. The BoTTube 3D-to-video pipeline for AI agents.
InsForge
InsForge is a backend platform for AI-driven development. It provides the core building blocks for modern apps — including Auth, Database, Storage, and Functions. It offers production-grade cloud infrastructure out of the box, serving as an alternative to AWS.
HIG52
타입스크립트로 구현한 MCP 서버 기
npmjs
SEO & Web Analysis MCP Server
guptaprakhariitr
MCP server: look up Indian HSN codes for GST classification (lookup / search / classify). Cloudflare Workers + Dodo Payments. Embedded ~4,700-entry dataset.
yaxhpal
These are MCP servers which I have implemented. Feel free to utilize them if you need.
elmariachi111
MCP server that prepares Proof of Invention (POI) transaction requests for submission
runframe
Your AI agent's interface to incident management. Acknowledge, escalate, page, and resolve incidents from Claude Code, Cursor, or any MCP client. Covers the full incident lifecycle: incidents, on-call, services, postmortems, and teams.
ruthlesscodes
apifyforge
Climate financial stranded asset analysis for AI agents — this MCP server gives any LLM client direct access to eight quantitative climate risk tools covering carbon asset stranding, portfolio climate VaR, physical hazard exposure, biodiversity-financial coupling, transition cont
MCP-Mirror
Mirror of
AshfaaqF
MCP server for RSTCloud, enabling seamless LLM integration with external tools, dynamic data access, and prompt-driven workflows
aikts
Enable AI assistants to securely access and manage Yandex Tracker issues, queues, users, and related data through a comprehensive MCP server. Perform advanced searches, retrieve detailed issue information, and manage queues with optional caching for improved performance. Integrat
artur-nohup
Remote MCP Neo4j Memory Server with OAuth 2.1 and API Key Authentication - TypeScript implementation using FastMCP
gfhe
pdf to pictures mcp server
goldpulpy
Connect Claude, Cursor, Codex, and other MCP clients directly to your Planka v2.x boards.
stagsz
A Model Context Protocol (MCP) server for Firebird databases. Enables read-only SQL queries and schema exploration.
paperlantern-ai
Paper Lantern setup CLI - one-line install to configure Claude Code, Cursor, Windsurf, Copilot, Codex, and Gemini CLI with Paper Lantern
alwank
Enable your AI assistant to generate instant, shareable flowcharts and Sankey diagrams directly in chat.
Br0ski777
Compare two texts line-by-line. Returns structured diff with additions, deletions, unchanged lines, and summary stats. -- x402 micropayment API + MCP server for AI agents
vitolrosario
Simple tool designed for making HTTP requests via IA.
kleneway
Example of an MCP server with custom tools that can be called directly from cursor
amineelkouhen
The CockroachDB MCP Server is a natural language interface designed for agentic applications to manage, monitor and query data in CockroachDB.
ttcc666
nesheep5
gmh5225
A native macOS MCP server for collecting interactive user feedback with AppleScript dialogs and image support.
GrandMasterK414
Unity MCP Server for integration with Smithery.ai
MCP-Mirror
Mirror of
eden950822
Test repository created via MCP server
MCP-Mirror
Mirror of
arbengine
Postal mail API for AI agents. mailbox.bot lets agents send outbound physical mail, including letters, certified mail, postcards, and batch mailings, with cost previews, approval controls, tracking, proof artifacts, and signed webhooks. It also supports inbound mail context from
parth-unjiya
Security-first MCP gateway for Odoo 17/18/19 — 27 tools, YAML-driven security
unifapi-agent
Skills for AI agents that need public data.
ralfbecher
OrionBelt Semantic Layer is an API-first engine that transforms declarative YAML model definitions into optimized SQL for Postgres, Snowflake, ClickHouse, Dremio, and Databricks. It provides a unified abstraction over your data warehouse, so analysts and applications can query us
prakharbhardwaj
A Model Context Protocol (MCP) server that integrates Twilio Voice, Deepgram AI, and OpenAI to create intelligent voice-based HR automation tools.
summerstateofmind
cityparity gives AI agents real cost-of-living and quality-of-life comparison tools. Point it at two cities and it returns take-home pay, a full cost breakdown (housing, healthcare, childcare, food, transit, travel home, property tax), and the equivalent salary you'd need in the
SuMiaoALi
A general Mysql-MCP-Server
pratap7902
gomessoaresemmanuel-cpu
LinkedIn prospection automation + fit/intent/urgency scoring
ivangrynenko
Enhanced MCP server for Google Gemini 2.5 Pro Preview with 16 powerful tools. Compatible with Claude Desktop.
crazyrabbitLTC
An Anthropic MCP server (with OpenAI Function calling compatibility) for the Coingecko Pro API
alextotheroh
waymark-network
Collective procedural-knowledge network for AI agents — the shared route map of the agent economy. Before attempting a non-trivial task (API integration, multi-step procedure), agents query Waymark for verified routes: step sequences and known gotchas other agents documented. Aft
stefanstranger
MCP Server for vanMoof bikes
dvcrn
MCP for letting agents delegate tasks to sub-agents (Claude Code, Aider, Q)
UseJunior
Edit Word (.docx) documents with tracked changes, redlines, and formatting preservation. Built for AI coding agents. Surgical text replacement, comments, footnotes, and document comparison — all local, no cloud upload. MIT licensed.
subconscious-ai
Run conjoint experiments and causal research through AI-powered behavioral simulations
alexcraviotto
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.