MCP servers · connect in Claude Desktop

Claude Desktop MCP servers

3,432 MCP servers have a connect command for Claude Desktop. 1,660 are SAFE, 638 CAUTION and 1,134 BLOCK. Every one was read in full before it was listed.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude Desktop MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/for/claude-desktop/page/123

Verdicts · 3,432 servers

✓SAFE1,660!CAUTION638✕BLOCK1,134

Transports

A server can list more than one transport.

Tool risk

1,009

servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 9 tools.

Servers with no destructive tools →

3,432 servers for Claude Desktop

2,929–2,952 of 3,432 · ranked by trust score, then stars

AgentChat

shy2593666979/agentchat

✕BLOCK F

AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。

★ 9022 readstdio

DB

freepeak/db-mcp-server

✕BLOCK F

A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.

★ 4312 writestreamable-http

Context-Engine

context-engine-ai/context-engine

✕BLOCK F

Context-Engine MCP - Agentic Context Compression Suite

★ 4021 destructivesse

Synapse AI

synapseorch-ai/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

Sudocode

sudocode-ai/sudocode

✕BLOCK F

Lightweight agent orchestration dev tool that lives in your repo

★ 2933 writestdio

dsh-config-manager

xiajiajun516/dsh-config-manager

✕BLOCK F

DeepSeek Harness (DSH) backup & restore plugin — export, import, migrate and sync your complete DSH configuration, plugins, MCP servers, skills and workspace. One-click migration to another machine.

★ 1842 writestreamable-http

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

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

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

DuckDB MCP Native

theseedship/duckdb_mcp_node

✕BLOCK F
★ 41 destructivestdio

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

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

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

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

ue-mcp

db-lyon/ue-mcp

✕BLOCK F

Complete Unreal Engine development toolkit exposed as MCP tools.

★ 4074 readstdio

Story UI

southleft/story-ui

✕BLOCK F

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

★ 2341 destructivesse

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

More about Claude Desktop

Other client hubs

By risk

Questions

How do I add an MCP server to Claude Desktop?
Paste the JSON block shown on the server's page into the mcpServers section of Claude Desktop's configuration file.
Which Claude Desktop MCP servers are safe?
Of the 3,432 servers with a Claude Desktop connect command, 1,660 are SAFE, 638 CAUTION and 1,134 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?
1,261 of the 3,432 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.