MCP Servers

A directory of curated & open-source Model Context Protocol servers. Search and discover MCP servers to enhance your AI capabilities.

Sora

An MCP server to generate and remix videos with OpenAI's Sora 2 API directly from MCP clients like Claude, Cursor, and VS Code.

MarkItDown

Exposes Microsoft's powerful MarkItDown Python utility as a lightweight MCP server to feed documents, images, and audio into any AI model.

Imagician

Open-source MCP server for image editing operations. Convert formats, resize, crop, and optimize images using AI assistants with simple commands.

Chrome DevTools

Official Google Chrome DevTools MCP server provides AI coding assistants direct browser control, performance tracing, and real-time debugging capabilities.

PGMCP

An MCP server that connects AI assistants to any PostgreSQL database for natural language querying with read-only, secure access.

Gemini DeepSearch

An automated MCP server that uses Gemini models and Google Search to perform deep, multi-step web research and provide citation-rich answers.

Atlassian

Set up the MCP Atlassian server to connect your AI assistant with Jira and Confluence. Supports Cloud, Server, and Data Center via Docker.

Laravel Boost

Install the Laravel Boost MCP server to connect AI tools directly to your app's database, routes, and documentation for better coding.

Cloudflare

Access Cloudflare's complete service ecosystem through natural language with MCP servers for Workers, analytics, security, DNS, and more infrastructure management.

Node.js Debugger

An MCP server for full-featured Node.js debugging using the Chrome DevTools Protocol. Let AI assistants set breakpoints and inspect variables.

MCP Django

A Model Context Protocol (MCP) server for Django that offers read-only project exploration and an optional stateful shell for AI-assisted development.

Browser AI

Control browser automation using natural language. The Browser AI MCP server intelligently maps commands to Playwright tools.

SigNoz

Get SigNoz alert details, service top operations, or dashboard configs through your AI assistant. Uses MCP protocol, Go-built, open-source.

Run Python

An MCP server for executing Python code securely in a sandboxed environment using Pyodide and Deno.

iPhone

An MCP server for automating iPhone tasks using Appium. Control apps, interact with the UI, and capture screenshots via a streamable HTTP API.

Crash

An advanced MCP server featuring revision mechanisms, flexible validation, and session management for complex analytical tasks and multi-step reasoning.

Datascript

Run complex queries on your in-memory DataScript DB with any MCP client. Features graph search and visualization.

EventWhisper

Pure Python MCP server for filtering Windows event logs by time, EventID, and keywords without PowerShell execution or host commands.

ShadowGit

Use the ShadowGit MCP Server to connect AI tools like Claude to your code history. Run git log, diff, and blame commands from your AI.

SearXNG Mul MCP

A Model Context Protocol (MCP) server for SearXNG that supports multi-query parallel search via stdio and HTTP.

FAQs

Q: What exactly is the Model Context Protocol (MCP)?

A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.

Q: How is MCP different from OpenAI's function calling or plugins?

A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.

Q: Can I use MCP with frameworks like LangChain?

A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.

Q: Why was MCP created? What problem does it solve?

A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.

Q: Is MCP secure? What are the main risks?

A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.

Q: Who is behind MCP?

A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.

Get the latest & top AI tools sent directly to your email.

Subscribe now to explore the latest & top AI tools and resources, all in one convenient newsletter. No spam, we promise!