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.
Cite
Cite this page
ModelsAtlas. “Claude Desktop MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/for/claude-desktop/page/131
Verdicts · 3,432 servers
Transports
- stdio, runs locally2,258
- Streamable HTTP, remote1,126
- SSE, legacy remote321
- Not declared657
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
3,121–3,144 of 3,432 · ranked by trust score, then stars
Prompts Server
sparesparrow/mcp-prompts
Model Context Protocol server for managing, storing, and providing prompts and prompt templates for LLM interactions.
Pentest
ramkansal/pentestmcp
pentestMCP: AI-Powered Penetration Testing via MCP, an MCP designed for penetration testers.
Vibe Coder
freshtechbro/vibe-coder-mcp
Vibe-Coder-MCP server extends AI assistants with specialized software development tools.
Swiss Caselaw
jonashertner/caselaw-repo-1
Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch
Teradata
teradata/teradata-mcp-server
The community development of a MCP server for a Teradata database
Kali
zebbern/zebbern-kali-mcp
MCP server for Kali toolkit (docker) - 121 tools for AI-assisted security testing give agents access to all it needs!
Profullstack
profullstack/mcp-server
A generic, modular server for implementing the Model Context Protocol (MCP).
Fastly
fastly/mcp
Model Context Protocol (MCP) server for AI-powered Fastly CDN management.
Barbacane
barbacane-dev/barbacane
Barbacane API and Bidirectional AI Gateway
governance-sdk
lua-ai-global/governance
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
Agent 007
bill10/agent-007
From web terminals for your coding agents to a self-running agent company: Claude Code and Codex in parallel git worktrees, a job board they pick work from, and one agent that runs the board from a goal.
browser-ipc-cdp
alexis14kl/browser-ipc-cdp
browser-ipc-cdp — Control remoto de navegadores Chromium (Brave, Chrome, Edge) via IPC con CDP dinámico. Abre tu navegador real con todas tus sesiones, detecta o asigna puerto automáticamente, configura portproxy/firewall para WSL, y actualiza el MCP de Claude Code. Sin puertos fijos, sin hacks
hbhqq9-bde-score
hbhqq9/bde-score
🏆 Open-source multi-factor stock scoring API (0-100) | US/HK/A-Share 74 stocks | Zero signup | shields.io badges | GitHub Action | EU AI Act compliant
limetry
limetry/limetry
Limetry is open-source agent action governance: check tool intents against policy before irreversible runs. Returns allow, deny, or approval_required with signed receipts and privacy-safe audit. TypeScript SDK, CLI, and MCP for IDE like Cursor, VS Code, GitHub Copilot, Claude. Optional CI, SQL, and
sfdt
scoobydrew83/sfdt
Salesforce DevTools — CLI, VS Code extension, sf plugin, MCP server, and web dashboard for Salesforce DX deploy, test, org health, and release management. AI-optional, CI-ready.
Synorive
arturoaeriform174/Synorive
Search your files by meaning and fact-check the web, fully offline.
GPT Researcher
assafelovic/gpt-researcher
An autonomous agent that conducts deep research on any data using any LLM providers
vMLX
jjang-ai/vmlx
vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm
FLUJO
mario-andreschak/FLUJO
Multi-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. NextJs+React
Canonry <img src="https://raw.githubusercontent.com/Canonry/
Canonry/canonry
Agent-first AI SEO (AEO/GEO) operating platform
agents-can-communicate
automatis-tools/agents-can-communicate
Messages between AI coding sessions in different vendors' clients, such as Claude Code and Codex. Local, open source, no lead agent.
OrionBelt
ralforion/orionbelt-semantic-layer
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
OrionBelt Semantic Layer
ralfbecher/orionbelt-semantic-layer
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
DeployStack
deploystackio/deploystack
Open source MCP hosting - deploy MCP servers to HTTP endpoints for n8n, Dify, Voiceflow, and any MCP client.
More about Claude Desktop
Other client hubs
By risk
Questions
How do I add an MCP server to Claude Desktop?
Which Claude Desktop MCP servers are safe?
Are any of these servers remote?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- How do I add an MCP server to Claude Desktop?
- Which Claude Desktop MCP servers are safe?
- Are any of these servers remote?