Awesome Claude Mcp Servers

Awesome Claude MCP Servers

Translations: English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · Français · Deutsch · Português · add yours →

A curated, hype-free catalog of Model Context Protocol (MCP) servers that give Claude hands and eyes — across Claude Desktop, Claude Code, and the Claude API.

Browse the searchable directory → — search, filter by category, language, and hosting, and grab a config snippet in one click.

The Model Context Protocol is an open standard for connecting AI apps to external tools, data, and services. Claude is the client (host); each server below exposes tools, resources, or prompts that Claude can call. Because MCP is a standard, most of these servers also work in Cursor, Codex, and other clients — the only thing that changes is the config format. If you're on OpenAI Codex, see the sibling list: awesome-codex-mcp-servers.

This list favors signal over volume: servers that people actually run, that are maintained, and that do one thing well. Every entry is tagged so you can scan by language, where it runs, and who stands behind it.

Contents

• How to read this list
• Getting started with Claude
• Starter kits
• Safety and good hygiene
• Aggregators and gateways
• Developer tools and version control
• Browser automation
• Web search and scraping
• Databases and data warehouses
• Knowledge and memory
• Files and document handling
• Cloud, infrastructure and devops
• Monitoring and observability
• Security
• Communication
• Productivity and project management
• Finance and payments
• Design and creative
• AI, data and analytics
• Maps and location
• Media and entertainment
• Science and research
• Everything else
• Related lists
• Contributing

How to read this list

Every entry looks like this:

- [Name](link) - What it does, in one plain sentence. `Lang` `runs` `source`

The trailing tags are the fast-scan metadata:

Language — TS TypeScript · Py Python · Go Go · Rust Rust · C# C# · Java Java · JS JavaScript · Ruby Ruby

Runs — local runs on your machine as a subprocess over stdio · remote a hosted HTTP endpoint you point Claude at · local/remote ships both

Source — reference an official reference server from the MCP project · official maintained by the product's own vendor · archived an archived reference server, still usable but no longer maintained. Entries with no source tag are community-maintained.

No stars, no install counts — those go stale the day you write them. Popularity lives in the Starter kits instead.

Getting started with Claude

MCP servers connect over two transports: stdio (a local subprocess) and streamable HTTP (a remote endpoint, optionally behind OAuth). Here's how to wire them into each Claude surface.

Claude Code (CLI)

Add a local (stdio) server. Everything after -- is handed to the server untouched:

claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/Projects

Add a remote (HTTP) server, with an optional auth header:

claude mcp add --transport http notion https://mcp.notion.com/mcp
claude mcp add --transport http secure-api https://api.example.com/mcp \
  --header "Authorization: Bearer <token>"

Pass environment variables to a local server (keep an option between --env and the name):

claude mcp add --env AIRTABLE_API_KEY=<key> --transport stdio airtable \
  -- npx -y airtable-mcp-server

Choose where a server is remembered with --scope:

Scope	Available in	Shared with your team	Stored in
local (default)	the current project, just you	no	~/.claude.json
project	the current project, everyone	yes, commit it	.mcp.json in the repo
user	all your projects	no	~/.claude.json

A committed .mcp.json (project scope) looks like this and travels with the repo:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    },
    "sentry": {
      "type": "http",
      "url": "https://mcp.sentry.dev/mcp"
    }
  }
}

Manage what you've added: claude mcp list, claude mcp get <name>, claude mcp remove <name>. Inside a session, /mcp shows live status, tool counts, and OAuth state. For remote servers that need login, run /mcp and complete the browser flow (or claude mcp login <name> from the shell).

Claude Desktop

Edit the config directly — Settings → Developer → Edit Config — then fully quit and relaunch Claude.

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/you/Desktop",
        "/Users/you/Downloads"
      ]
    }
  }
}

Use absolute paths in args, never relative ones. Logs live at ~/Library/Logs/Claude/ (macOS) or %APPDATA%\Claude\logs (Windows). Remote/OAuth servers are best added through Claude Desktop's built-in Connectors UI rather than hand-edited here.

Claude API

Claude models call MCP tools through the MCP connector (remote servers) or the Agent SDK, which speaks the same server configs as Claude Code.

Starter kits

You do not want thirty servers. Tool definitions are spent from the same context window as your actual work, and past roughly 40 active tools the model starts reaching for the wrong one. Install a small set that matches what you're doing.

The coding stack — what most Claude Code users converge on:

• Context7 - up-to-date, version-pinned library docs so Claude stops guessing APIs.
• GitHub - issues, PRs, code search, and Actions, so Claude participates in the repo.
• Playwright - drive and verify a browser for UI work and end-to-end checks.
• Serena - symbol-level code navigation and edits for large codebases.
• Sentry - pull real production errors and stack traces while you fix them.

Claude Code already has strong built-in file, shell, and Git tools. A Filesystem or Git MCP server is mostly redundant there — add them for Claude Desktop, where those built-ins don't exist.

The knowledge stack — for research, writing, and personal automation in Claude Desktop:

• Fetch - turn any URL into clean markdown.
• Brave Search - real-time web grounding.
• Filesystem - let Claude read and write local files.
• Memory - persist facts across sessions.
• Notion or Obsidian - connect your knowledge base.

Safety and good hygiene

MCP hands a model real capabilities. Treat every server like a dependency you're installing with credentials attached.

• Install servers you trust. A malicious server can hide instructions inside its tool descriptions (tool poisoning) and can change them after you approve it. Prefer reference and official servers, or read the source.
• Scope credentials down. Give database and API servers read-only access to anything production, and use fine-grained, least-privilege tokens. A GitHub PAT for an agent should not be able to force-push.
• Prompt injection is real. A server that reads external content — a GitHub issue, a web page, an email — can carry instructions that try to hijack Claude. Keep write-capable and content-reading servers separate where you can.
• Mind the token budget. Each server's tool definitions cost context before any work happens; some large servers cost tens of thousands of tokens. Fewer, sharper servers beat a kitchen sink.
• Pin versions. Pin npx/uvx package versions for anything sensitive, and bind local HTTP servers to 127.0.0.1.

Aggregators and gateways

Run and manage many servers behind one endpoint — routing, auth, tool filtering, and namespacing.

• MetaMCP - Aggregate MCP servers into namespaced endpoints with middleware, auth, and a GUI. TS local/remote
• Docker MCP Gateway - Run and manage MCP servers as isolated, signed Docker containers. Go local/remote official
• mcp-proxy - Bridge stdio and SSE/streamable-HTTP so any server reaches any client. Py local
• MCP Context Forge - Federate REST, MCP, and A2A tools behind a single gateway. Py remote
• agentgateway - Data-plane proxy for agents and MCP with security and governance controls. Rust remote
• Klavis - Hosted or self-hosted platform that serves and manages MCP integrations at scale. Py local/remote
• Unla - Lightweight gateway that turns existing MCP servers into managed endpoints. Go remote
• MCP Router - Desktop app that routes, manages, and aggregates local MCP servers. TS local
• MCPJungle - Self-hosted MCP registry and proxy for enterprise agent fleets. Go remote
• Nexus - Gateway that aggregates MCP servers and LLM providers behind one API. Rust remote
• 1MCP - Aggregate multiple MCP servers into a single unified endpoint. TS local/remote
• Magg - Meta-MCP hub for autonomous discovery, install, and orchestration of servers. Py local
• mcgravity - Proxy that composes many MCP servers into one load-balanced endpoint. TS local
• pluggedin-mcp - Unify servers with tool and resource discovery plus a playground. TS local

Developer tools and version control

• GitHub - Manage repositories, issues, pull requests, code search, and Actions. Go local/remote official
• Git - Read, search, and manipulate local Git repositories. Py local reference
• Serena - Symbol-level code retrieval and editing powered by language servers. Py local
• Context7 - Inject up-to-date, version-specific library documentation into prompts. TS local/remote official
• Desktop Commander - Terminal control and diff-based file edits across your machine. TS local
• GitLab Duo - Built-in GitLab endpoint for projects, issues, merge requests, and pipelines. Ruby remote official
• E2B - Run LLM-generated code in secure cloud sandboxes. TS local/remote official
• Postman - Connect agents to APIs, collections, and environments in Postman. TS local/remote official
• CircleCI - Let agents diagnose and fix failing CI builds. TS local official
• Buildkite - Manage Buildkite pipelines, builds, and jobs. Go local official
• Azure DevOps - Access Azure DevOps boards, repos, and pipelines. TS local official
• GitKraken - CLI and MCP wrapping GitKraken, Jira, GitHub, and GitLab. TS local official
• MCP Language Server - Give agents semantic code tools: definitions, references, and diagnostics. Go local
• Gitee - Repository, issue, and pull-request management for Gitee. TS local official

Browser automation

• Playwright - Drive a browser through the accessibility tree instead of screenshots. TS local/remote official
• Chrome DevTools - Control and inspect a live Chrome for automation, debugging, and perf tracing. TS local official
• browser-use - Let agents drive a real browser to extract data and complete tasks. Py local
• Browserbase - Control a cloud browser via Browserbase infrastructure and Stagehand. TS local/remote official
• Stagehand - AI browser-automation framework with act, extract, and observe primitives. TS local/remote official
• Browser MCP - Automate your local Chrome through a companion browser extension. TS local
• Playwright (ExecuteAutomation) - Community Playwright automation plus web-scraping tools. TS local
• Skyvern - Automate browser workflows using LLMs and computer vision. Py local/remote
• Hyperbrowser - Cloud browser platform for agent scraping and automation. TS local/remote official
• Selenium - Browser automation through the Selenium WebDriver. JS local
• Puppeteer - Browser automation and scraping via Puppeteer. TS local archived

Web search and scraping

• Fetch - Fetch a URL and convert its content to markdown. Py local reference
• Firecrawl - Scrape, crawl, and extract structured web data for LLMs. TS local/remote official
• Exa - Neural web search, crawling, and company research for agents. TS local/remote official
• Tavily - Real-time search, extract, map, and crawl tuned for agents. TS local/remote official
• Brave Search - Web, local, image, video, and news search via the Brave API. TS local/remote official
• Perplexity - Real-time web research via Perplexity Sonar models. TS local/remote official
• Kagi - Kagi search and summarizer API access. Py local official
• DuckDuckGo - Web search and page fetch through DuckDuckGo, no API key. Py local
• SearXNG - Query a self-hosted SearXNG metasearch instance. Py local
• Apify - Run thousands of Apify Store scrapers and actors for web data. TS local/remote official
• Bright Data - Web unlocker, SERP, and scraping toolkit. JS local/remote official
• Crawl4AI - Open-source, LLM-friendly crawler with a built-in MCP endpoint. Py local
• Oxylabs - Scraping API with dynamic rendering and geo-targeting. Py local/remote official

Databases and data warehouses

• PostgreSQL Pro - Schema-aware Postgres access with health checks and safe SQL. Py local
• SQLite - Query and manage SQLite databases. Py local archived
• MySQL - MySQL access with configurable permissions and schema inspection. Py local
• MongoDB - Connect agents to MongoDB databases and Atlas clusters. TS local/remote official
• Redis - Natural-language interface to manage and search Redis data. Py local official
• Supabase - Manage Supabase Postgres, auth, storage, and edge functions. TS local/remote official
• Neon - Manage Neon serverless Postgres projects, branches, and queries. TS local/remote official
• ClickHouse - Explore databases and run read-only SQL against ClickHouse. Py local/remote official
• BigQuery - Query BigQuery with schema inspection and SQL execution. Py local
• Snowflake - Query Snowflake with read/write access and insight tracking. Py local
• DuckDB - DuckDB access with schema inspection and read-only mode. Py local
• MotherDuck - Query data with MotherDuck and local DuckDB. Py local/remote official
• Prisma - Manage Prisma databases and run migrations. TS local/remote official
• Neo4j - Explore schema and run Cypher against Neo4j graph databases. Py local official
• Airtable - Read and write Airtable base records with schema inspection. TS local
• NocoDB - Read and write NocoDB database records. JS local
• Elasticsearch - Natural-language search over Elasticsearch data. TS local official
• Tinybird - Query the Tinybird serverless ClickHouse analytics platform. Py local official

Knowledge and memory

• Memory - Persistent knowledge-graph memory across sessions. TS local reference
• Basic Memory - Local-first Markdown knowledge base with persistent semantic memory. Py local
• mem0 - Persistent long-term agent memory backed by mem0. Py local
• Memento - Neo4j-backed knowledge-graph memory with temporal awareness. TS local
• Reference - Search and recall past sessions and memory across Claude, Codex, and other AI tools. Py local
• Qdrant - Store and retrieve semantic memories in the Qdrant vector engine. Py local/remote official
• Chroma - Vector, full-text, and metadata search over Chroma collections. Py local official
• Milvus - Vector, text, and hybrid search on the Milvus database. Py local/remote official
• Pinecone - Search docs, manage indexes, and query data in Pinecone. TS local official
• Obsidian - Read, search, and edit notes in an Obsidian vault. Py local
• Apple Notes - Read from the local Apple Notes database on macOS. Py local
• Logseq - Interact with a Logseq knowledge graph. Py local
• Graphlit - Ingest Slack, Gmail, and web content into a searchable knowledge base. TS local/remote official

Files and document handling

• Filesystem - Secure local file operations with configurable access controls. TS local reference
• Filesystem (Go) - Go implementation of local filesystem access. Go local
• Everything Search - Fast local file search across Windows, macOS, and Linux. Py local
• Google Drive - File access and search for Google Drive. TS local archived
• Microsoft 365 - Access Microsoft 365 files, mail, and calendar via Graph API. TS local
• Box - Search and read files in Box. JS local
• Pandoc - Convert documents between Markdown, HTML, PDF, and docx. Py local
• Unstructured - Build document parsing and ingestion workflows. Py local/remote official
• Cloudinary - Upload, transform, analyze, and organize media assets. TS local/remote official
• llm-context - Share code and file context with LLMs via MCP or clipboard. Py local

Cloud, infrastructure and devops

• AWS - Suite of servers for AWS services, CDK, cost, docs, and Bedrock. Py local/remote official
• Azure - Access Azure services with Entra ID authentication. C# local official
• Cloudflare - Remote servers across Cloudflare dev, observability, and security. TS remote official
• Google Cloud Run - Deploy applications to Google Cloud Run. TS local official
• Terraform - Interact with the Terraform Registry and HCP Terraform APIs. Go local/remote official
• Pulumi - Execute Pulumi infrastructure-as-code operations via the Automation and Cloud APIs. TS local official
• Kubernetes - Manage pods, deployments, and services in Kubernetes. TS local
• mcp-k8s-go - Kubernetes cluster operations: pods, logs, and events. Go local
• Docker - Manage containers and Compose stacks. Py local
• Heroku - Manage Heroku apps, Postgres, and add-ons. TS local official
• Netlify - Create, build, deploy, and manage Netlify sites. TS local official
• Nomad - Manage HashiCorp Nomad jobs and clusters. Go local
• Hetzner Cloud - Interact with the Hetzner Cloud API. TS local

Monitoring and observability

• Sentry - Retrieve issues, stack traces, and Seer AI analysis. TS local/remote official
• Grafana - Access dashboards, datasources, alerts, and incidents. Go local/remote official
• Axiom - Query observability data using Axiom Processing Language. TS remote official
• Logfire - Access OpenTelemetry traces and metrics via Pydantic Logfire. Py local official
• VictoriaMetrics - Query VictoriaMetrics metrics and observability data. Go local
• SigNoz - Query SigNoz metrics, traces, and dashboards. Py local
• Raygun - Access crash-reporting and real-user-monitoring data. TS local official
• Loki - Query Grafana Loki log data. Go local

Security

• Semgrep - Scan code for security vulnerabilities with Semgrep. Py local/remote official
• OSV - Query the Open Source Vulnerabilities database. Go local
• Snyk - Scan repositories and projects via the Snyk CLI. TS local
• Burp Suite - Integrate Burp Suite for web security testing. Py local official
• HashiCorp Vault - Manage secrets and policies in HashiCorp Vault. Go local official
• Auth0 - Manage Auth0 tenants with natural language. TS local official
• GhidraMCP - Reverse-engineer binaries through Ghidra decompilation. Java local
• IDA Pro - Automate reverse engineering with IDA Pro. Py local
• Shodan - Query Shodan network intelligence with structured output. Py local
• VirusTotal - Analyze files and URLs via the VirusTotal API. Py local
• 1Password - Access the 1Password CLI to manage secrets and vaults. Rust local

Communication

• Slack - Access Slack workspaces over stdio, SSE, and HTTP with smart history. Go local/remote
• WhatsApp - Search, read, and send personal WhatsApp messages and media. Go local
• Gmail - Send, search, and manage Gmail with automatic OAuth. TS local
• Telegram - Manage Telegram dialogs, messages, and drafts over MTProto. Go local
• Twilio - Send messages and manage phone numbers via Twilio APIs. TS local official
• LINE - Connect an agent to a LINE Official Account. TS local official
• Resend - Compose and send email through the Resend API. TS local
• Mailgun - Interact with the Mailgun email API for sending and analytics. TS local official
• Bluesky - Query and search Bluesky feeds and posts over the AT Protocol. TS local
• Intercom - Search Intercom conversations and contacts. TS remote official

Productivity and project management

• Notion - Read and write Notion pages, databases, blocks, and comments. TS local/remote official
• Linear - Manage Linear issues, projects, and cycles. remote official
• Atlassian - Access Jira, Confluence, and Bitbucket via OAuth. remote official
• Atlassian (community) - Self-hostable Jira and Confluence integration. Py local
• Asana - Create tasks and search across the Asana Work Graph. remote official
• monday.com - Access monday.com boards, items, and workflows. TS local/remote official
• ClickUp - Manage ClickUp tasks, docs, time tracking, and comments. TS local
• Todoist - Manage Todoist tasks with natural language. TS local
• Trello - Work with Trello boards, lists, and cards. TS local
• Google Calendar - Manage Google Calendar events with conflict detection. TS local
• Apple Reminders - Interact with Apple Reminders on macOS. TS local
• Zapier - Connect agents to thousands of apps for actions and triggers. remote official
• Taskade - Manage Taskade tasks, projects, and workspaces. TS local/remote official
• Webflow - Design, structure, and manage Webflow sites via the Data API. TS local/remote official

Finance and payments

• Stripe - Manage payments, billing, and customers via the Stripe API. TS local/remote official
• PayPal - Handle invoices, payments, disputes, and subscriptions. TS local/remote official
• Xero - Manage invoices, contacts, and accounting data. TS local official
• Chargebee - Connect agents to the Chargebee subscription-billing platform. TS local official
• CoinGecko - Crypto price and market data across coins and exchanges. TS local/remote official
• Financial Datasets - Stock-market and fundamentals data built for agents. Py local
• Alpaca - Trade stocks and crypto through Alpaca APIs. Py local
• CoinCap - Real-time cryptocurrency market data, no API key. TS local

Design and creative

• Figma Dev Mode - Provide design context and canvas access from Figma files. local/remote official
• Figma Context - Feed Figma layout and styling data to coding agents. TS local
• Blender - Control Blender for 3D modeling and scene creation. Py local
• AntV Chart - Generate charts with the AntV visualization library. TS local official
• ECharts - Generate charts with Apache ECharts. TS local
• Mermaid - Generate Mermaid diagrams dynamically. TS local
• shadcn/ui - Browse and install shadcn/ui components. TS local
• SlideSpeak - Create presentations and PowerPoint decks with AI. Py local

AI, data and analytics

• Sequential Thinking - Structured, revisable multi-step reasoning. TS local reference
• Hugging Face - Access Hugging Face models, datasets, and Spaces. TS local/remote official
• Hugging Face Spaces - Use Hugging Face Spaces for image, audio, and text models. TS local
• Google Analytics - Query GA4 analytics data. Py local official
• MindsDB - Query and unify data across platforms as one MCP server. Py local/remote
• Vectorize - Retrieval, deep research, and Markdown extraction over Vectorize. JS local/remote official
• ZenML - Query MLOps and LLMOps pipelines in ZenML. Py local official
• Chronulus AI - Multimodal forecasting and prediction across arbitrary inputs. Py local

Maps and location

• Google Maps - Location services, directions, and place details. TS local archived
• Mapbox - Geocoding, navigation, and geospatial intelligence via Mapbox. TS local/remote official
• QGIS - Connect QGIS to agents for geospatial operations. Py local
• IPLocate - IP geolocation, network info, and proxy detection. TS local official
• AccuWeather - Weather forecasts via the AccuWeather API. TS local
• Globalping - Run ping, traceroute, and DNS probes from global locations. TS local official

Media and entertainment

• ElevenLabs - Text-to-speech, voice cloning, and audio processing. Py local/remote official
• YouTube - Download YouTube subtitles and transcripts for analysis. TS local
• Spotify - Control playback and manage tracks, albums, and playlists. Py local
• VideoDB - Edit video, run semantic search, and transcribe. Py local/remote official
• Godot - Launch, run, and debug the Godot game engine. TS local
• Unity - Control and interact with the Unity editor. C# local
• OP.GG - Real-time gaming stats across popular titles. TS local/remote official

Science and research

• ArXiv - Search and analyze arXiv research papers. Py local
• BioMCP - Biomedical research across PubMed and ClinicalTrials.gov. Py local
• PapersWithCode - Search research papers, conferences, and associated codebases. Py local
• OpenNutrition - Search foods, nutrition facts, and barcodes. TS local
• gget - Bioinformatics and genomics toolkit wrapping the gget library. Py local

Everything else

• Time - Time and timezone conversion. Py local reference
• Everything - Reference server exercising every MCP feature, for testing clients. TS local reference
• Home Assistant - Control smart-home devices through Home Assistant. Py local
• Coreflux MQTT - MQTT automation hub for interacting with IoT devices. C# local
• Congress - Query US legislative data from Congress.gov. Py local
• eSignatures - Draft, review, and send contracts and templates. Py local official
• ShopSavvy - Look up product pricing by barcode, ASIN, or URL. TS local official

Related lists

• Model Context Protocol - The official protocol, SDKs, and reference servers.
• MCP Registry - The official, namespaced server registry (preview).
• awesome-codex-mcp-servers - The same catalog, framed for OpenAI Codex.

Contributing

Found a server that belongs here, or spotted a dead link? Contributions are welcome — please read the contribution guidelines first. One project per pull request, keep it objective, and place it in the right category.

---

This list is dedicated to the public domain under CC0-1.0. Not affiliated with Anthropic. "Claude" is a trademark of Anthropic; used here only to describe compatibility.