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.
MCP-Mirror
Mirror of
SiddheshDongare
A GitHub MCP Server
ahmaxdev
AI Git workflow MCP server. Generates conventional commit messages, branch names, PR descriptions, and manages work streams (wip, hotfix, review, experiment). Works with Cursor, Claude Desktop, Claude Code, Windsurf, and VS Code. Install: pip install gitrama-mcp
pgpt-dev
MCP Server for Private GPT
hamnhugs
Test repository for GitHub MCP server validation
wty0512
A Model Context Protocol (MCP) server to provide git tools for LLM Agents, with fixes for the amend parameter caching issue
ceshine
An MCP server that offers several commands for generating prompts or contexts from Jira content
wricardo
MCP server to interact with a git repository
MCP-Mirror
Mirror of
oghenetejiriorukpegmail
A test repository created using the GitHub MCP server
ryanbrito
akbxr
Gitlab MCP Server for Zed
nextDriveIoE
yosay-org
Documentation and configuration details for GitHub MCP server setup
vipink1203
A powerful Model Context Protocol (MCP) server for GitHub Enterprise that enables AI agents to access and manage enterprise users, organizations, and licenses.
cbruyndoncx
MCP Servers focused collection of repo's (using git-subrepo for easy updating --ALL)
MCP-Mirror
Mirror of
MCP-Mirror
Mirror of
StargrrlMoonlight
This Repo is a playground for Vibe Coding using GitHub Agent Mode in VS Code and various MCP Servers. All done through the editor - development, testing, GitHub environments / Actions, issues etc.
James-Chahwan
Structural graph memory for AI coding assistants. repo-graph maps your codebase entities, relationships, and feature flows so the model navigates to the right files instead of reading everything first. Tree-sitter, 20+ languages, frontend to backend and more, any MCP client.
ProCreations-Official
A Model Context Protocol (MCP) server that provides GitHub integration for AI assistants like Claude. Now supports Anthropic Integrations for remote connectivity!
bmeyer99
guptarajiv535
MCP server poc python
JavaProgrammerLB
CDataSoftware
This read-only MCP Server allows you to connect to GitHub data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).
mowgli-ai
Mowgli is an intelligent product canvas that connects to your coding agent over MCP or as an Agent Skill. Use it to turn an existing frontend or GitHub repo into pixel-perfect, editable React + Tailwind designs, iterate on them in natural language, and sync the results back into
rujutaranade
JIRA MCP Server: Essential API Integrations for Technical Program Managers
ankitkapur1992-hlido
Independent, evidence-backed reviews of AI agents — machine-readable scorecards, claim audits, C2PA-signed proof. Public data mirror of hlido.eu
rihofujino
jitendrajaware
A Model Context Protocol (MCP) server that allows Claude and other AI assistants to create and manage Jira issues.
MCP-Mirror
Mirror of
haydulski
mcp server
Foxhunt
CDataSoftware
This read-only MCP Server allows you to connect to Jira data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at
pratik-mahalle
sanskarmk
This is a test repository created by test script of MCP Server for GitHub
mixuechu
tomo-cps
GitHub MCP Server implementation and testing repository
MCP-Mirror
Mirror of
marvelouscypherman
MCP server for using the GitHub API
ground-creative
A set of powerful tools designed for seamless integration with GitHub via MCP
birariro
MCP server for find agoda hotel reviews
noushad999
The lean GitHub MCP server for Claude — 26x smaller responses, 19 tools, zero Docker required.
MCP-Mirror
Mirror of
chromewillow
MCP server for analyzing and converting Git repositories to text files for LLM context
almas7202
This repository complements or interacts with the github-mcp-server project.
VisualDudek
A repository for testing MCP server implementations and related projects.
IamSAL
sidharthrajaram
kich555
MCP-Mirror
Mirror of
final-il
MCP Server handling GitHub/GitLab integrations
abhinavchoubey2000
A Model Context Protocol server implementation for GitHub integration
dvcrn
5amfung
MCP Jira Server
Arman-ali-khan-786
Repository for MCP server
sanskarmk
This is a test repository created by test script of MCP Server for GitHub
PrajwalDhiwar
Github MCP Server for Cursor or Claude
sanskarmk
This is a test repository created by test script of MCP Server for GitHub
pablo-peek
Repo Context MCP provides programmatic access to repository contents for integrations and automation. It can list directories/files, read any file, return the README, perform TypeScript type analysis (via ts-morph), and search for OpenAPI/Swagger spec files. Supports local repo p
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.