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/191

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

4,561–4,584 of 4,761 · ranked by trust score, then stars

webhooks-cc

kroqdotdev/webhooks-cc

✕BLOCK F

Webhook inspection and testing service

★ 23 destructivestdio

mcp-writ

strumbyte/mcp-writ

✕BLOCK F

Policy enforcement, OS sandboxing, and JSON-RPC auditing for MCP servers

★ 02 write

Basic Memory

basicmachines-co/basic-memory

✕BLOCK F

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

★ 4,0161 destructivestdio

BetterDB Monitor

betterdb-inc/monitor

✕BLOCK F

Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

★ 1,3011 destructivestdio

Gemini-Flow

clduab11/gemini-flow

✕BLOCK F

rUv's Claude-Flow, translated to the new Gemini CLI; transforming it into an autonomous AI development team.

★ 3871 destructive

DevOps AI Toolkit

vfarcic/dot-ai

✕BLOCK F

Intelligent dual-mode agent for deploying applications to ANY Kubernetes cluster through dynamic discovery and plain English governance

★ 3362 destructivestreamable-http

MCPOmni Connect

abiorh001/mcp_omni_connect

✕BLOCK F

An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, every run survives a crash without silently redoing anything, every step on the record.

★ 24918 readsse

IJFW

ferroxlabs/ijfw

✕BLOCK F

IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.

★ 2122 write

Kiln

codeofaxel/Kiln

✕BLOCK F

Describe it or draw it — Kiln makes it real. The open-source MCP server for 3D printing: AI agents (Claude, Codex, Cursor, or any MCP client) design, generate, slice & print on Bambu Lab, Creality, Prusa, Elegoo, Klipper/Moonraker, OctoPrint, Duet/RepRapFirmware & any Marlin printer.

★ 906 destructivestdio

Claude Total Memory

vbcherepanov/total-agent-memory

✕BLOCK F

Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.

★ 713 destructivestdio

Dunetrace

dunetrace/dunetrace

✕BLOCK F

The runtime reliability layer for AI agents.

★ 681 writesse

PAI Knowledge OS

mnott/PAI

✕BLOCK F

Personal AI Infrastructure

★ 522 writestdio

Obsidian LLM Wiki

2233admin/obsidian-llm-wiki

✕BLOCK F

Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't guess.

★ 369 readstdio

derive

derive-to/derive

✕BLOCK F

Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.

★ 301 destructivestdio

nimblebrain

NimbleBrainInc/nimblebrain

✕BLOCK F

Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.

★ 256 destructivesse

5dive-plugins

5dive-ai/5dive-plugins

✕BLOCK F

Multi-harness plugin marketplace maintained by 5dive — Telegram bridge and related agent-channel integrations.

★ 21 destructivestdio

ghost

wcatz/ghost

✕BLOCK F

GhostMem — a local-first MCP memory server for Claude Code, opencode, Cursor, and other MCP clients.

★ 21 writestdio

open-health-sync

soma-intelligence/open-health-sync

✕BLOCK F

Self-hosted, open-source API for wearable and health data, in Go. Syncs Apple Health, Health Connect, Oura, WHOOP, Withings, Strava, Fitbit, Dexcom and more into one model, served over REST, FHIR R4, Open mHealth, CSV/Parquet, webhooks and a read-only MCP server. Docker, Helm, Raspberry Pi. AGPL-3.0

★ 1Not listed in sourcestdio

seiche

beepboop2025/seiche

!CAUTION F

Free AGPL funding and market-context research for international workflows. A LiquiLens product, connected to institution evidence and Undertow liquidity via API/MCP.

★ 1Not listed in sourcestdio

@forumone/throughline

forumone/throughline

✕BLOCK F
★ 01 destructive

@tangle-network/agent-app

tangle-network/agent-app

✕BLOCK F

A feature-full starting point for production agent applications on Tangle.

★ 04 destructivestdio

open-brx

tony99nyr/open-brx

✕BLOCK F

Open-source platform for Battle Company BRX laser taggers: hosted game modes, live scoring, custom weapons and a laptop Mission Control on stock guns over Bluetooth LE. Also the source of The Ultimate BRX Manual.

★ 01 destructive

SmythOS

smythos/sre

✕BLOCK F

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

★ 1,2921 destructivesse

ecc-agentshield

affaan-m/agentshield

✕BLOCK F

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

★ 1,27411 writestreamable-http

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.