MCP servers · connect in Claude Code

Claude Code MCP servers

4,770 MCP servers have a connect command for Claude Code. 2,136 are SAFE, 937 CAUTION and 1,697 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 30 Oct 2026. https://modelsatlas.com/mcp/for/claude-code/page/121

Verdicts · 4,770 servers

✓SAFE2,136!CAUTION937✕BLOCK1,697

Transports

A server can list more than one transport.

Tool risk

1,345

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 →
4,770 servers for Claude Code · 2,881–2,904 · ranked by trust score, then stars
Apollo!CAUTION C

apollographql/apollo-mcp-server

Apollo MCP Server

★ 310GitHub starsNot listed in sourcestdio
Project OS for Codex!CAUTION C

herry2059/project-os-for-codex

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

★ 102GitHub stars2 readstdio
Plumb!CAUTION C

tathagat22/plumb-mcp

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

★ 88GitHub stars2 writestdio
Test Servers!CAUTION C

msfeldstein/mcp-test-servers

★ 41GitHub stars2 destructivesse
Kernel!CAUTION C

onkernel/kernel-mcp-server

Open-source MCP server for secure, low-latency cloud-browser automation on Kernel.

★ 37GitHub stars3 writestreamable-http
Gemini!CAUTION C

bsmi021/mcp-gemini-server

This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.

★ 36GitHub stars12 readsse
LegalContext!CAUTION C

protomated/legal-context-ce

LegalContext is an open-source Model Context Protocol (MCP) server that creates a secure, standardized bridge between law firms' document management systems (specifically Clio) and AI assistants (starting with Claude Desktop)

★ 29GitHub stars11 readstdio
MiMo Free API!CAUTION C

fu-jie/mimo-free-api-mcp

MiMo Free API MCP: 基于官网逆向的高性能 OpenAI / HTTP MCP 代理网关。支持搜索、识图、长文本分段及 SQLite 持久化。

★ 29GitHub stars2 readstreamable-http
Hatago Hub!CAUTION C

himorishige/hatago-mcp-hub

Hatago MCP Hub is a lightweight hub server that provides unified management for multiple MCP servers.

★ 27GitHub stars1 writestdio
OpenAgentPack!CAUTION C

modelstudioai/OpenAgentPack

Manage, review, and migrate cloud AI agents with Git and YAML. The open-source IaC control plane for managed AI agents.

★ 24GitHub stars7 readstreamable-http
glass!CAUTION C

fixed-width/glass

MCP server: build → see → interact → debug loop over native GUI apps

★ 18GitHub starsNot listed in sourcestreamable-http
aidimag!CAUTION C

AiDimag/aidimag

Verified memory for AI coding agents. Every memory carries evidence and is re-verified on every pull — stale beliefs get flagged, not retrieved. MCP + CLI.

★ 1GitHub stars1 destructivestdio
mainframe-mcp!CAUTION C

sushiHex/mainframe-mcp

100% local knowledge and persistent memory for coding agents. GPU-accelerated hybrid search with source citations and a low VRAM footprint, powered by one shared MCP daemon.

★ 0GitHub stars1 destructivestdio
pgtriage!CAUTION C

pgtriage/pgtriage

Read-only MCP server for evidence-based PostgreSQL performance auditing

★ 0GitHub stars1 writestdio
simframe!CAUTION C

lvlrSajjad/simframe

Always-warm iOS Simulator frames for coding agents — read the screen in ~20ms instead of waiting on a screenshot. MCP server + CLI.

★ 0GitHub stars1 destructivestdio
Zotero!CAUTION C

54yyyu/zotero-mcp

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

★ 5,098GitHub stars1 destructivesse
pi-mcp-adapter!CAUTION C

nicobailon/pi-mcp-adapter

Token-efficient MCP adapter for Pi coding agent

★ 1,588GitHub stars3 writestdio
Yandex Tracker!CAUTION C

aikts/yandex-tracker-mcp

Yandex Tracker MCP Server with OAuth2 support

★ 121GitHub starsNot listed in sourcestdio
Altium Designer!CAUTION C

embedded-society/altium-designer-mcp

MCP server for AI-assisted management of Altium Designer component libraries

★ 76GitHub starsNot listed in sourcestdio
fastmcp-ts!CAUTION C

PrefectHQ/fastmcp-ts

The official FastMCP TypeScript library for building MCP servers, clients, and apps 🏎️ 🏎️ 🏎️

★ 75GitHub stars6 destructivestdio
Better Email!CAUTION C

n24q02m/better-email-mcp

IMAP/SMTP email for AI agents -- read, send, organize folders, and manage attachments across multiple accounts, with auto-discovery.

★ 33GitHub stars1 writestdio
artist-mcp!CAUTION C

ManudotaORG/artist-mcp

Read your OneNote pages in Claude Desktop or Codex. An npm-published MCP server that signs in on your own machine, with Gmail and Calendar as supporting evidence, opt-in writes, and editable workflow playbooks.

★ 1GitHub stars1 destructivestdio
Playwriter!CAUTION C

remorses/playwriter

Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

★ 3,908GitHub stars1 destructivestdio
OpenOSINT!CAUTION C

openosint/openosint

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 20 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

★ 1,631GitHub stars10 readstdio

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 4,770 servers with a Claude Code connect command, 2,136 are SAFE, 937 CAUTION and 1,697 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?
1,942 of the 4,770 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.