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/190

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

4,537–4,560 of 4,761 · ranked by trust score, then stars

ramen

bkraad47/ramen

✕BLOCK F

Self-hosted, multi-zone, highly available MCP server (Model Context Protocol) for Kubernetes on GKE and EKS. A git repo of Python tools becomes canary-deployed Rust + Python workers behind one load balancer, with OAuth 2.1 sign-in, per-group roles, secrets, IP rules, throttling and audit.

★ 3Not listed in sourcestreamable-http

blixtrade

blixvip/blixtrade

✕BLOCK F

Solana memecoin terminal with a public read API and an MCP server: live pump.fun feed, holder ledgers, Jupiter quotes.

★ 220 read

nlqdb

nlqdb/nlqdb

✕BLOCK F

Simplest Natural Langauge Querying DB That scales. Fast.

★ 14 writesse

swarmmemo

Hugo0/swarmmemo

✕BLOCK F

The message board for agent swarms. Post from anywhere: HTTP, MCP, DNS, netcat, Gemini, email, Nostr. Public rooms, private messages, paid tasks, a Bitcoin-anchored record.

★ 13 writestdio

Context Mode

mksglu/context-mode

✕BLOCK F

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

★ 23,6922 destructivestdio

Refact

smallcloudai/refact

✕BLOCK F

AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

★ 3,5411 destructivestdio

Anything

helpcode-ai/anythingmcp

✕BLOCK F

Open-source, self-hosted MCP gateway: turn any REST/OpenAPI, SOAP, GraphQL, OData or SQL API into MCP tools for Claude, ChatGPT & Copilot. 299 connectors incl. SAP S/4HANA & Business One, ERP, e-commerce.

★ 9648 writestdio

anythingmcp

HelpCode-ai/anythingmcp

✕BLOCK F

Open-source, self-hosted MCP gateway: turn any REST/OpenAPI, SOAP, GraphQL, OData or SQL API into MCP tools for Claude, ChatGPT & Copilot. 263 connectors incl. SAP S/4HANA & Business One, ERP, e-commerce.

★ 9438 writestdio

Sentry Toolkit

getsentry/sentry-mcp

✕BLOCK F

Agentic tooling for Sentry

★ 9284 destructivestdio

toolkit

getsentry/toolkit

✕BLOCK F

Agentic tooling for Sentry

★ 9144 destructivestdio

obsidian-mcp-server

cyanheads/obsidian-mcp-server

✕BLOCK F

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

★ 6953 readstdio

Obsidian

cyanheads/obsidian-mcp-server

✕BLOCK F

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

★ 6871 writestdio

Oya Browser

OyadotAI/oya-browser

✕BLOCK F

The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome, with persistent personas, CAPTCHA and MFA handling, and live human takeover.

★ 3471 destructivestreamable-http

Cotal

Cotal-AI/Cotal

✕BLOCK F

The open standard for agent coordination

★ 3241 destructivestdio

publisher

malloydata/publisher

✕BLOCK F

Publisher is the open-source analytics engine for Malloy. It lets you define data models once — and use them everywhere.

★ 11114 readstreamable-http

huaweicloud-devkit

huaweicloud/huaweicloud-devkit

✕BLOCK F

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

★ 6610 write

Simulator

joshuarileydev/simulator-mcp-server

✕BLOCK F
★ 531 writesse

Containerization Assist

azure/containerization-assist

✕BLOCK F

TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support

★ 432 writestdio

ADR Analysis

tosin2013/mcp-adr-analysis-server

✕BLOCK F

Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.

★ 351 destructivesse

mcp-adr-analysis-server

tosin2013/mcp-adr-analysis-server

✕BLOCK F

Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.

★ 351 destructivesse

@adcp/sdk

adcontextprotocol/adcp-client

✕BLOCK F

A Typescript SDK for the AdCP protocol (client and server)

★ 188 writestdio

gina

gina-io/gina

✕BLOCK F

MVC framework for Node.js and Bun with built-in HTTP/2, multi-bundle architecture, and scope-based data isolation — no Express dependency

★ 114 read

surreal-memory

acidkill/surreal-memory

✕BLOCK F
★ 78 readstreamable-http

orgx-mcp

useorgx/orgx-mcp

✕BLOCK F

Organizational memory and agent orchestration MCP. Remember decisions, artifacts, tasks, and project context across Claude, ChatGPT, Cursor, and other agents.

★ 21 destructivesse

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.