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/169

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

4,033–4,056 of 4,761 · ranked by trust score, then stars

GitLab

zereight/gitlab-mcp

!CAUTION F

First gitlab mcp for you, building together

★ 1,99835 destructivesse

Vet

safedep/vet

✕BLOCK F

Protect against malicious open source packages 🤖

★ 1,107Not listed in sourcestdio

ThinkWatch

thinkwatchproject/thinkwatch

✕BLOCK F

Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and cost tracking across OpenAI, Anthropic, Gemini, and self-hosted LLMs.

★ 8142 readstreamable-http

Context

neuledge/context

✕BLOCK F

Local-first documentation for AI agents

★ 4173 readstdio

ue-mcp

db-lyon/ue-mcp

✕BLOCK F

Complete Unreal Engine development toolkit exposed as MCP tools.

★ 4074 readstdio

Shodh-Memory

varun29ankus/shodh-memory

✕BLOCK F

Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.

★ 3018 destructivestdio

Story UI

southleft/story-ui

✕BLOCK F

AI-powered Storybook story generator — works with any framework, any design system, any LLM provider

★ 2341 destructivesse

Task Orchestrator

jpicklyk/task-orchestrator

✕BLOCK F

Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.

★ 2076 readstdio

Context Sync

intina47/context-sync

✕BLOCK F

Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.

★ 1903 writestdio

Context Lattice

sheawinkler/contextlattice

✕BLOCK F

The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.

★ 1531 readstreamable-http

Copilot Money

ignaciohermosillacornejo/copilot-money-mcp

✕BLOCK F

MCP server for Copilot Money App - AI powered personal finance queries using local data

★ 834 destructivestdio

Linear Streamable

iceener/linear-streamable-mcp-server

✕BLOCK F

MCP Server for interacting with Linear API. Written in TypeScript, Node and Hono.dev

★ 711 readstreamable-http

Netlify Examples

netlify/examples

✕BLOCK F

A collection of examples and demonstrations to help people building the web with Netlify

★ 671 writestreamable-http

Globalping

jsdelivr/globalping-mcp-server

✕BLOCK F

Remote MCP server that gives LLMs access to run network commands

★ 6411 readsse

Talkito

robdmac/talkito

✕BLOCK F

TalkiTo lets developers interact with AI systems through speech across multiple channels (terminal, API, phone). It can be used as both a command-line tool and a Python library.

★ 5415 writesse

fury-antidetect-browser

furyteamtop/fury-antidetect-browser

✕BLOCK F

Free, open-source anti-detect browser. A Chromium 155 fork that spoofs the fingerprint in C++ rather than with injected JavaScript, with per-profile personas and proxies, a built-in MCP server for AI assistants, and a self-hostable team server with per-project access. No seats, no per-profile pricin

★ 536 write

Algorand

goplausible/algorand-mcp

✕BLOCK F

Algorand Local Model Context Protocol (Server & Client)

★ 446 destructivestdio

Ludus

noctedefensor/ludusmcp

✕BLOCK F
★ 411 destructivestdio

Dense-Mem

markhuangai/dense-mem

!CAUTION F

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

★ 396 readstreamable-http

Slack

jtalk22/slack-mcp-server

✕BLOCK F

Put your agent inside your Slack. Zero bots, zero admin queues, no Business+ upgrade — 20+ tools for stealth search, thread parsing and mention tracking. Every message attributed. Your session never leaves your Mac.

★ 312 destructivestdio

Docpull

raintree-technology/docpull

✕BLOCK F

Local-first Python CLI and MCP server for versioned, cited context from web and document sources.

★ 281 writestdio

agentdeals

robhunter/agentdeals

!CAUTION F

Catalogue of developer infrastructure free tiers, startup credits and pricing, with side-by-side vendor comparisons for hosting, databases and AI APIs. Website, JSON API and MCP server, read by coding agents choosing a stack.

★ 2212 readstdio

SatisfactoryMCP

lukszi/SatisfactoryMCP

✕BLOCK F

MCP server and local interactive map for Satisfactory — plan factories, trace logistics, and explore your world, all read straight from your own save files.

★ 62 destructive

0xray

0xRayAI/xray

✕BLOCK F

Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw

★ 23 destructivestdio

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.