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/168

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

4,009–4,032 of 4,761 · ranked by trust score, then stars

Ultimate

dicklesworthstone/ultimate_mcp_server

✕BLOCK F

Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems

★ 1611 writesse

Nitan

nitansde/nitan-mcp

✕BLOCK F

MCP client and Skill for US Card Forum

★ 1231 writestdio

Codebase

anrgct/autodev-codebase

✕BLOCK F

A vector embedding-based code semantic search tool with MCP server and multi-model integration. Can be used as a pure CLI tool. Supports Ollama for fully local embedding and reranking, enabling complete offline operation and privacy protection for your code repository

★ 1221 writesse

Apple RAG

bingowon/apple-rag-mcp

✕BLOCK F

MCP server providing AI agents with instant access to Apple developer documentation via RAG

★ 120Not listed in sourcestreamable-http

Agent Tool Protocol

mondaycom/agent-tool-protocol

✕BLOCK F

Agent Tool Protocol

★ 1014 destructive

Trvl

mikkoparkkola/trvl

✕BLOCK F

Travel MCP server + CLI for AI assistants — flights, hotels, trains, cars, ferries, price alerts. No API keys, single Go binary. 1 smart MCP tool + 66 aliases (98.9% smaller tools/list). Works with Claude, Cursor, Windsurf, Codex.

★ 86Not listed in sourcestdio

Agent Mako

drhalto/agentmako

✕BLOCK F

Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.

★ 542 destructivestdio

Curion

geanatz/curion

!CAUTION F

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.

★ 3311 readstdio

Dbmcp

haymon-ai/dbmcp

✕BLOCK F

Database MCP server for MySQL, MariaDB, PostgreSQL, and SQLite - with builtin PII redaction and write-prevention

★ 32Not listed in sourcestdio

Roku Dev Studio

paramount-engineering/roku-dev-studio

✕BLOCK F

Cross-platform Electron desktop studio for Roku developers: remote control, device queries, sideload, telnet console, RALE/App Connector, BrightScript Fiddle, JSON Action Scripts, an `rds` CLI, an MCP server for AI agents, and an internet relay.

★ 321 write

note.com MCP Server

shimayuz/note-com-mcp

✕BLOCK F

note.com用MCPサーバー(移行済)

★ 301 destructivestdio

Speclock

sgroy10/speclock

✕BLOCK F

Action guardrails for AI coding agents — native Claude Code enforcement, MCP integrations, and Git/CI checks.

★ 252 destructivestdio

footprintjs

footprintjs/footPrint

✕BLOCK F

The flowchart pattern for backend code — self-explainable systems that AI can reason about. Causal traces, auto-generated tool descriptions, transactional state.

★ 2015 read

ai-hist

AgentWorkforce/relayhistory

✕BLOCK F

Sync & search Claude Code + Codex CLI conversation history in SQLite. Zero dependencies.

★ 131 destructivestdio

ssh-mcp

YawLabs/ssh-mcp

✕BLOCK F

MCP server for SSH operations with built-in diagnostics

★ 62 destructivestdio

DuckDB MCP Native

theseedship/duckdb_mcp_node

✕BLOCK F
★ 41 destructivestdio

brokre

Furowu/brokre

✕BLOCK F

AI-safe credential broker for MCP — run saved SSH/MySQL/psql aliases; passwords never reach AI.

★ 3Not listed in sourcestdio

repopilot

azen07508-debug/repopilot

✕BLOCK F

Release gate for public GitHub repositories. Give it a repo URL and it returns a ship-or-block verdict with file-and-line evidence, the fixes that clear the gate, and the deployment plan and launch copy you ship with. HTTP + MCP. Static analysis only; no code execution.

★ 31 writestdio

rocky

poggufanz/rocky

!CAUTION F

A blind alien engineer who listens to your terminal, never forgets, and makes sure you still understand your own code.

★ 21 destructive

log10x-mcp

log-10x/log10x-mcp

✕BLOCK F

Log10x MCP Server — per-pattern log cost attribution for AI assistants (Claude, Cursor, Claude Desktop)

★ 11 destructivestdio

triumvirate

michaeljboscia/triumvirate

!CAUTION F

Five AI agents. One coordination layer. No relay server. Plus a trust layer that checks whether the review actually happened.

★ 116 readstreamable-http

fcvm

carlosbravoa/fcvm

✕BLOCK F

Disposable, isolated microVMs with container ergonomics, for people and agents: Firecracker VMs from any OCI image, snapshots and fork, jailer and network isolation, web console, MCP server

★ 0Not listed in sourcestdio

Reasonbook

kneelinghorse/reasonbook

✕BLOCK F

Reasonbook: decisions that survive the session, in a local record AI agents keep.

★ 01 destructivestdio

tool-control-plane

Abhishek-chohan/tool-control-plane

✕BLOCK F

The unglamorous half of agent tooling: a gRPC control plane for sessions, machines, fenced writes, and capability-scoped keys. HTTP and MCP gateways; Python, TypeScript, and Go SDKs.

★ 07 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 4,761 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.