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/159

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 · 3,793–3,816 · ranked by trust score, then stars
Qdrant!CAUTION D

mhalder/qdrant-mcp-server

MCP server for semantic search using local Qdrant vector database and OpenAI embeddings

★ 36GitHub stars4 destructivestdio
Carrot AI PM✕BLOCK D

talvinder/carrot-ai-pm

Carrot auto-writes specs and catches AI code drift. MCP server for Cursor that AST-validates every commit.

★ 29GitHub stars2 destructivestdio
Puppeteer Real Browser✕BLOCK D

withlinda/puppeteer-real-browser-mcp-server

Provides AI assistants with powerful, detection-resistant browser automation capabilities built on ZFC Digital's puppeteer-real-browser package.

★ 26GitHub stars1 writestdio
@waniwani/sdk✕BLOCK D

WaniWani-AI/sdk

Build distribution MCPs: multi-step conversational funnels (lead gen, booking, quotes) that run as a single MCP tool in ChatGPT, Claude, and Cursor. A typed state graph compiles to one MCP tool.

★ 18GitHub stars1 write
yorishiro-proxy✕BLOCK D

usk6666/yorishiro-proxy

AI-native MITM proxy — MCP server for traffic interception, recording & replay

★ 17GitHub stars1 writestreamable-http
MCPg!CAUTION D

devopam/MCPg

Postgres MCP Server

★ 13GitHub stars1 readstdio
career-compass-mcp✕BLOCK D

benskamps/career-compass-mcp

Turn Claude into a full job-search partner — Career KB, tailored resumes, application pipeline, interview prep. MCP server + local dashboard; your data never leaves your machine.

★ 6GitHub stars3 writestdio
expense✕BLOCK D

assaf/expense

Forward a receipt to your inbox and it's filed automatically.

★ 6GitHub stars2 writestreamable-http
mcp-server✕BLOCK D

pipeshub-ai/mcp-server

This repository contains the packages that make up Pipeshub’s local MCP server

★ 6GitHub stars1 writesse
open-memex✕BLOCK D

stoneskin/open-memex

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs.

★ 4GitHub stars2 writestdio
orbit-vsx✕BLOCK D

oaslananka/orbit-vsx

VS Code extension for MCP health, debug-session intelligence, and A2A trust workflows: monitor companion services, inspect Agent Cards, enforce workspace trust, and expose bounded tools to agent mode.

★ 3GitHub stars1 read
dibs✕BLOCK D

Agenxy/dibs

Keeps your agents in the loop about each other. See what the fleet is doing, then message, sync and send files between agents. Dibs reports; it never acts.

★ 2GitHub stars21 readstreamable-http
中文✕BLOCK D

Akira-TL/forgerelay

Local development control plane for MCP coding agents.

★ 1GitHub stars1 destructivestdio
agentic-coding-harness✕BLOCK D

sblattj/agentic-coding-harness

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.

★ 1GitHub stars6 writestreamable-http
Blender Model Context Protocol✕BLOCK D

ahujasid/blender-mcp

Community plugin to control Blender 3D with any LLM of your choice

★ 29,036GitHub stars1 write
MCP TypeScript SDK!CAUTION D

modelcontextprotocol/typescript-sdk

The official TypeScript SDK for Model Context Protocol servers and clients

★ 13,561GitHub stars8 destructivesse
Reverse Engineer Anything✕BLOCK D

morluto/rea

Reverse engineer anything with agents, from app behavior down to native binaries.

★ 8,470GitHub stars1 writestdio
excel-mcp-server✕BLOCK D

haris-musa/excel-mcp-server

A Model Context Protocol server for Excel file manipulation

★ 4,215GitHub starsNot listed in sourcestdio
MCP Scan✕BLOCK D

invariantlabs-ai/mcp-scan

Security scanner for AI agents, MCP servers and agent skills.

★ 3,080GitHub stars1 destructivestdio
QueryWeaver✕BLOCK D

falkordb/queryweaver

An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.

★ 1,080GitHub starsNot listed in sourcestreamable-http
Iai!CAUTION D

codeabra/iai-mcp

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

★ 901GitHub stars2 writestdio
Xcode✕BLOCK D

r-huijts/xcode-mcp-server

MCP Server implementation for Xcode integration

★ 384GitHub stars4 destructivestdio
Mengram✕BLOCK D

alibaizhanov/mengram

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

★ 204GitHub stars2 destructivestdio
Pgconsole✕BLOCK D

pgplex/pgconsole

Minimal Postgres editor for speed, collaboration, and AI

★ 155GitHub stars2 destructivestreamable-http

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.