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.
movva09
Agentic MCP Client Server that solves a math task and draws output in rectangle in a drawing app.
pgavali0318
Persistent AI memory layer for developers. Stores decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf. 8 MCP tools including get_context, add_memory, search_decisions, and team workspaces. Never re-explain your st
kochenevsky
Track and grow your brand visibility across AI assistants: ChatGPT, Perplexity, Claude, Gemini, and more. Semantica AI MCP server gives AI assistants direct access to AI visibility analytics — monitor brand mentions in LLM responses, run visibility scans, analyze competitors, tra
Rakesh1002
Official MCP server for AgentDrive — cross-agent artifact workspace with provenance. 20 tools over stdio or hosted at mcp.agentdrive.sh.
Tencent-RTC
It exposes Tencent RTC SDK documentation and Tencent RTC API resources to LLM-based tools. This improves the ability of LLM AI Agent to understand and interact with the Tencent RT SDK and API.
davidmosiah
hemant-zangoh
Complete development environment setup for Claude Code with MCP servers, dev containers, and long-running job capabilities
muxi1998
laksh753
MCP Server Repository
ogulcanarbc
mcp server assistant for mock data
carvectorio
Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes.
ptitiwat2543
bleedmode
Tells you how you and your Claude agent actually work together. Reads your CLAUDE.md, hooks, skills, memory, and scheduled tasks — then writes you a letter. Three core tools: collab (collaboration scoring + lint), security (secrets scan, prompt-injection surfaces, rule conflicts)
john-broadway
The Proxmox MCP you can hand the keys — VE + Backup Server + Mail Gateway on one audited trust core (plan, prove, undo, diagnose). 325 tools, MCP + A2A.
gpitrella
Multi-platform AI memory. One save, recall everywhere—Claude, ChatGPT, Cursor, VS Code, and more. Persistent memory across AI conversations and clients.
fbettag
OpenAI Deep Research MCP Server enables AI assistants to conduct comprehensive, multi-step research through intelligent web search and content synthesis. Transforms complex research queries into structured, citation-backed reports without writing custom search logic. Features ite
KlausJager10110
Implement an MCP (Model Context Protocol) server with an AI agent using the OpenAI SDK and an OpenRouter base URL,
Sumedh1599
Uses Claude or OpenAI API to convert prompt-mapped input into concrete MCP server components such as tools, resource templates, and prompt handlers.
RohanMuppa
MCP server for Brightspace (D2L): check grades, due dates, announcements, rosters & more using Claude, ChatGPT, Cursor, or any MCP client. Built with TypeScript and the D2L REST API.
MathewTomberlin
A simple prototype SwarmUI MCP server with accompanying local LangChain Ollama agent
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.
jameshung2015
public server for mcp
noma-py
Gives AI agents a structured action manifest for any webpage — what's clickable, fillable, and submittable, so agents can act on a page instead of just reading it.
JackVitick
AI assistants help creators draft, schedule, and publish posts to 8 platforms (Instagram, Facebook, X, LinkedIn, Threads, Bluesky, TikTok, YouTube) through OAuth-authorized accounts with human-in-the-loop approval. Connect once, then draft and schedule from Claude, ChatGPT, or Cu
shoggi211
Repair malformed JSON from LLM tool calls and agent-to-agent handoffs — fixes trailing commas, single quotes, truncation, markdown code fences, comments, and python literals, and can validate/coerce the result against a JSON Schema. Free deterministic tier; pay-per-call LLM fallb
mannubaveja007
Academic Hub A professional network for researchers to publish, collaborate, and monetize their work. Powered by Google's Gemini LLM with MCP context server for intelligent research assistance, and integrated with the OCID Edu Chain ecosystem for secure identity management.
hblaDCOM
SQL Server Agent tool (with MCP)
newideas99
🧠 MCP server implementing RAT (Retrieval Augmented Thinking) - combines DeepSeek's reasoning with GPT-4/Claude/Mistral responses, maintaining conversation context between interactions.
kani3894
Python MCP server for Hevy fitness app. Log workouts with natural language, search exercises, manage routines. Features web interface, demo mode, and 22 MCP tools.
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.