MCP servers · connect in Claude Code

Claude Code MCP servers

4,761 MCP servers have a connect command for Claude Code. 2,135 are SAFE, 935 CAUTION and 1,691 BLOCK. Every one was read in full before it was listed.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude Code MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/for/claude-code/page/166

Verdicts · 4,761 servers

✓SAFE2,135!CAUTION935✕BLOCK1,691

Transports

A server can list more than one transport.

Tool risk

1,342

servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 10 tools.

Servers with no destructive tools →

4,761 servers for Claude Code

3,961–3,984 of 4,761 · ranked by trust score, then stars

Open Multi Agent

open-multi-agent/open-multi-agent

✕BLOCK F

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

★ 6,9978 writestreamable-http

Deep Research

u14app/deep-research

✕BLOCK F

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

★ 4,6892 writesse

fastCRW

fastcrw/crw

✕BLOCK F

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma

★ 1,1141 readstdio

Unreal Editor

db-lyon/ue-mcp

✕BLOCK F

Complete Unreal Engine development toolkit exposed as MCP tools.

★ 3824 readstdio

Synapse

naveenraj-17/synapse-ai

✕BLOCK F

Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local, cloud or CLIs.

★ 3271 destructivestdio

AutoPentest

bhavsec/autopentest-ai

✕BLOCK F

Agentic Pentesting MCP server that discovers, exploits, and reports web application vulnerabilities.

★ 23212 writestdio

Football Docs

withqwerty/football-docs

✕BLOCK F

Searchable football data provider documentation for AI coding agents. Like Context7 for football data.

★ 1942 destructivestdio

NotebookLM

roomi-fields/notebooklm-mcp

✕BLOCK F

Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

★ 1887 destructivestdio

www-project-agent-memory-guard

OWASP/www-project-agent-memory-guard

✕BLOCK F

OWASP Foundation web repository

★ 1835 readstdio

Vnsh

raullenchai/vnsh

✕BLOCK F

One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.

★ 1574 writestdio

apple-notes-mcp

sweetrb/apple-notes-mcp

✕BLOCK F

MCP server for Apple Notes - read, search, create, edit, organize, and export notes on macOS via Claude and other AI assistants

★ 1514 destructivestdio

Reshapr

reshaprio/reshapr

✕BLOCK F

The open source, no-code MCP Server for AI-Native API Access

★ 1282 read

SwiftLens

swiftlens/swiftlens

✕BLOCK F

SwiftLens is a Model Context Protocol (MCP) server that provides deep, semantic-level analysis of Swift codebases to any AI models. By integrating directly with Apple's SourceKit-LSP, SwiftLens enables AI models to understand Swift code with compiler-grade accuracy.

★ 1261 write

Sverklo

sverklo/sverklo

✕BLOCK F

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

★ 812 destructivestdio

Pi

TGYD-helige/pi

✕BLOCK F

Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — covering IM workspace integrations (Lark, DingTalk, WeCom), browser & computer automation, persistent memory, telemetry, task scheduling, image generation, web access, security policies, and m

★ 792 writestdio

Disco Connectors

stackonehq/mcp-connectors

✕BLOCK F

mcp connectors for disco

★ 7418 destructivestdio

Gofannon

the-ai-alliance/gofannon

✕BLOCK F

A web app for rapidly prototyping AI agents and the lightweight web UIs that wrap them—build flows, preview interactions, and share agent-driven experiences without lock-in.

★ 684 read

Research Hub

wenyuchiou/research-hub

✕BLOCK F

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

★ 6413 writestdio

Auth Step-by-Step

christian-posta/mcp-auth-step-by-step

✕BLOCK F

Step by step walkthrough of an MCP Authorization implementation

★ 621 read

Kollektiv

alexander-zuev/kollektiv-mcp

✕BLOCK F

Kollektiv MCP enables you to chat with and query your own documents directly from IDEs and MCP clients. Private, secure, and integrated into your favorite code editor

★ 611 read

Super

dhanababum/supermcp

✕BLOCK F

🚀 SuperMCP - Create multiple isolated MCP servers using a single connector. Build powerful Model Context Protocol integrations for databases (PostgreSQL, MSSQL) with FastAPI backend, React dashboard, and token-based auth. Perfect for multi-tenant apps and AI assistants.

★ 616 destructivestreamable-http

proximo

john-broadway/proximo

✕BLOCK F

The Proxmox MCP you can hand the keys. All four products: PVE, PBS, PMG, PDM.

★ 522 readstdio

Md Redline

dejuknow/md-redline

✕BLOCK F

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

★ 393 writestdio

Enquire

oomkapwn/enquire-mcp

✕BLOCK F

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

★ 345 writestdio

More about Claude Code

Other client hubs

By risk

Questions

How do I add an MCP server to Claude Code?
Run the claude mcp add command shown on the server's page; it names the package and its version.
Which Claude Code MCP servers are safe?
Of the 4,761 servers with a Claude Code connect command, 2,135 are SAFE, 935 CAUTION and 1,691 BLOCK. Cards are ranked by trust score, so the safest are first; open one to read its findings before you connect it.
Are any of these servers remote?
1,937 of the 4,761 list a remote transport (streamable HTTP or SSE). The rest run as a local process your client starts.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.