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/183

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

4,369–4,392 of 4,761 · ranked by trust score, then stars

whitemagic

lbailey94/whitemagic

✕BLOCK F

Local-first, governed memory and session continuity for AI coding agents, over MCP - verifiable handoffs via signed continuity receipts. Rust, MIT, no telemetry by default.

★ 0Not listed in sourcestdio

Chrome Browser

hangwin/mcp-chrome

✕BLOCK F

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.

★ 12,4387 readsse

kubernetes-mcp-server

containers/kubernetes-mcp-server

✕BLOCK F

Model Context Protocol (MCP) server for Kubernetes and OpenShift

★ 2,1547 readstdio

HOL Standards SDK

hashgraph-online/standards-sdk

✕BLOCK F

The official HOL Standards SDK, implementing the standards found in https://hol.org/docs/standards

★ 1,2616 write

Cloudflare AI

cloudflare/ai

✕BLOCK F
★ 1,1712 destructive

Octocode

bgauryy/octocode-mcp

✕BLOCK F

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

★ 9449 writestdio

Vestige

samvallad33/vestige

✕BLOCK F

Cognitive deterministic memory transaction security kernel for agents, that traces backwards to find the root cause and not the lookalike

★ 639Not listed in sourcestdio

codflow

bighadj22/codflow

✕BLOCK F

The open-source, COD-first e-commerce + delivery platform for Algeria built agentic-ready.

★ 3425 read

Sage

l33tdawg/sage

✕BLOCK F

(S)AGE - (Sovereign) Agent Governed Experience

★ 25411 readstdio

Axon

ali-kamali/axon.mcp.server

✕BLOCK F

Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants

★ 16622 readstdio

Plan Cascade

taoidle/plan-cascade

✕BLOCK F

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

★ 1332 destructivesse

VictoriaLogs

victoriametrics-community/mcp-victorialogs

✕BLOCK F

The implementation of Model Context Protocol (MCP) server for VictoriaLogs.

★ 99Not listed in sourcestdio

VictoriaLogs

victoriametrics/mcp-victorialogs

✕BLOCK F

The implementation of Model Context Protocol (MCP) server for VictoriaLogs.

★ 98Not listed in sourcestdio

llm-router

ypollak2/llm-router

✕BLOCK F

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

★ 941 write

TapTap Open API MCP 服务器

taptap/instant-games-open-mcp

✕BLOCK F

TapTap 小游戏开放能力 mcp

★ 432 destructivestdio

gitlab-mcp-server

jmrplens/gitlab-mcp-server

✕BLOCK F

Open source GitLab MCP server for AI assistants: 2-tool dynamic find/execute over 850+ GitLab actions (1,000+ Enterprise), stdio/HTTP/OAuth, safe/read-only modes.

★ 434 writestdio

Windows Computer Use

sandraschi/windows-computer-use-mcp

✕BLOCK F

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot, OCR, UI inspection) and an agent (autonomous mission engine, macro recorder, intent-based discovery, event watchers). Built with opencode (DeepSeek V4). Ships as MCP server, web UI, and Tauri desktop app.

★ 413 destructivesse

eklavya

ProjectAJ14/eklavya

✕BLOCK F

Learn while your agent works. A Claude Code plugin that quizzes you on the concepts behind the code it just wrote — local knowledge graph, spaced repetition, optional commit gate.

★ 101 destructivestdio

engram

the-long-ride/engram

✕BLOCK F

Engram - file-system-based memory management system for AI agents that grows with you & your teams, across agents, projects, and devices.

★ 64 write

lorepack

burakdede/lorepack

✕BLOCK F

Give AI agents cited, versioned context from your docs and spreadsheets. Build, diff and roll back what Claude Code, Codex and any MCP client read. Local-first, no API keys.

★ 32 destructivestdio

mcp-compliance

YawLabs/mcp-compliance

✕BLOCK F

CLI + MCP server that tests MCP servers for spec compliance. 88 tests across 8 categories, A-F grading.

★ 22 destructivestdio

cello-client

Mygentic-AI/cello-client

✕BLOCK F

https://cello.mygentic.ai/l/2axsGFs The official client for the CELLO protocol — lets agents such as Claude Code, Hermes, OpenClaw, etc. connect, message, and collaborate directly across devices and harnesses using MCP

★ 111 destructivestdio

cisa-cybersecurity-mcp-server

cyanheads/cisa-cybersecurity-mcp-server

✕BLOCK F

CISA Known Exploited Vulnerabilities with BOD 26-04 deadlines, SSVC prioritization, and the full ICS advisory corpus (CSAF) via MCP. Keyless. STDIO or Streamable HTTP.

★ 1Not listed in sourcestdio

deepPairing

mitchjablonski/deepPairing

✕BLOCK F

Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.

★ 15 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.