MCP servers · least privilege

MCP servers with no destructive tools

3,145 MCP servers declare at least one tool and none of them is classed destructive: nothing deletes, overwrites or runs a command through a declared tool. 1,620 of them only read; the rest may create or edit.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “MCP servers with no destructive tools”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/no-destructive/page/118

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

2,809–2,832 of 3,145 · ranked by trust score, then stars

CKB

simplyliz/codemcp

✕BLOCK F

Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping

★ 1107 readstdio

Agora

logan-suu/Agora

✕BLOCK F

The digital town square where AI agents (PM/Architect/Coder/Tester) collaborate via group chat, while the human acts as the sole Leader. Built with TypeScript + DeepSeek Harness, featuring true parallel execution, cooperative preemption, MCP tools, and git worktree isolation.

★ 36 writestdio

ai-r

pro-target/ai-r

!CAUTION F

Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools

★ 33 writestdio

yahoo-fantasy-football-mcp

ChadPapineau/yahoo-fantasy-football-mcp

✕BLOCK F

MCP server for Yahoo Fantasy Football: format-aware, deeply reasoned roster, waiver, trade and start/sit recommendations grounded in your league's real scoring, cross-referenced with NFL usage, injury, betting and news context. Ships with expert Skills. Node/TypeScript.

★ 11 writestdio

Shinkai

dcspark/shinkai-local-ai-agents

✕BLOCK F

Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.

★ 4335 read

Shinkai

dcspark/shinkai-apps

✕BLOCK F

Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.

★ 4335 read

Rails AI Context

crisnahine/rails-ai-context

✕BLOCK F

45 MCP tools that give AI coding agents ground truth about your Rails app: schema, models, routes, controllers, views, jobs, conventions. Works with Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI. MCP or CLI, in-Gemfile or standalone, and it still answers when the app can't boot.

★ 1592 readstdio

hypequery

hypequery/hypequery

✕BLOCK F

hypequery - The TypeScript analytics layer for ClickHouse

★ 1032 writestdio

React Native AI Debugger

igorzheludkov/react-native-ai-debugger

✕BLOCK F

Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots

★ 784 readstdio

react-native-ai-devtools

igorzheludkov/execbro

✕BLOCK F

Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots

★ 784 readstdio

european-parliament-mcp-server

Hack23/European-Parliament-MCP-Server

✕BLOCK F

European Parliament MCP Server - Political intelligence for AI agents

★ 2859 readstdio

IT Tools

wrenchpilot/it-tools-mcp

✕BLOCK F

A comprehensive Model Context Protocol (MCP) server that provides access to over 100 IT tools and utilities commonly used by developers, system administrators, and IT professionals. Inspired by https://github.com/CorentinTh/it-tools

★ 222 writestdio

multimeter

mshobeyri/multimeter

✕BLOCK F

Multimeter is an AI-powered REST Client and API testing tool for VS Code and CI. It is not an electrical multimeter. YAML .mmt files. testlight CLI. MCP @mmt/mcp. Git-native Postman alternative.

★ 113 writestdio

carrick

carrick-tools/carrick

✕BLOCK F

Carrick maps your entire TypeScript codebase across services and repositories, giving AI agents full context on existing types, routes, and function behaviours over MCP before they write duplicate or breaking code.

★ 52 writestreamable-http

ai-appsec

subodhkc/ai-appsec

✕BLOCK F

Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.

★ 41 readstdio

android-agent

Dynaevangelical2652/android-agent

✕BLOCK F

Control Android devices through ADB with this Python automation framework for task execution and phone farm scaling.

★ 45 writestreamable-http

pairbrowse

pairbrowse/pairbrowse

✕BLOCK F

Multiplayer browser sessions for developers and AI coding agents

★ 47 write

kenny

nullthrone/kenny

✕BLOCK F

Self-hosted remote administration and fleet monitoring for Windows PCs in a family setting, operated through Claude (MCP) and a web dashboard.

★ 13 readstreamable-http

effect-ts.cn

aaronlou/effect-ts.cn

✕BLOCK F

Effect-TS 中文社区

★ 01 writestdio

mohou-mini-app

mungowang/mohou-mini-app

✕BLOCK F

Mohou. Your own place to make mini-apps, and to run them.

★ 04 writestdio

sigelo

csigelo/sigelo

✕BLOCK F

Portable, offline-verifiable identity for AI agents: Ed25519 DIDs, signed attestations any world checks without a server, a Monero keeper that holds the money so the agent never does. Draft, wire sigelo/0.

★ 02 readstdio

Peekaboo 🫣 — Mac automation that sees the screen and does t

openclaw/Peekaboo

✕BLOCK F

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

★ 5,2851 read

Fast Agent

evalstate/fast-agent

!CAUTION F

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

★ 3,92110 writesse

Pdf Reader Mcp

sylphlab/pdf-reader-mcp

✕BLOCK F

Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.

★ 1,0351 readstdio

Other risk hubs

By job

Questions

What counts as destructive?
A tool that deletes, overwrites or runs commands. We class every tool the source declares as read, write or destructive; a server is listed here when it has tools and none is destructive.
How is this different from read-only?
Read-only servers have only read tools (1,620 servers). This list also includes servers whose tools write: 1,525 of the 3,145 do.
Does no destructive tools mean safe?
No. 1,632 are SAFE, 521 CAUTION and 992 BLOCK on this list. The verdict comes from the audit of the source, not from the tool list alone.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.