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/7

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

145–168 of 3,145 · ranked by trust score, then stars

E2B

e2b-dev/mcp-server

✓SAFE B

Giving Claude ability to run code with E2B via MCP (Model Context Protocol)

★ 3951 writestdio

VS Code Server

juehang/vscode-mcp-server

✓SAFE B

MCP server to expose VS Code editing features to an LLM for AI coding

★ 3955 writestreamable-http

AkTools

aahl/mcp-aktools

✓SAFE B

📈 提供股票、加密货币的数据查询和分析功能MCP服务器

★ 3911 writestdio

Maa

maa-ai/maamcp

✓SAFE B

基于 MaaFramework 的 MCP 服务器 为 AI 助手提供 Android 设备和 Windows 桌面自动化能力

★ 3871 write

Azan

ahmedeltaher/azan-mcp

!CAUTION B

Azan + Prayer Time + MCP + AI Agents + Islamic + Salah + A lightweight MCP library to calculate prayer times and trigger Azan with a single tool call. If you’re building an AI agent or prayer application, there’s no need to deal with astronomical calculations, timezones, or edge cases again.

★ 3836 write

Computer Use

domdomegg/computer-use-mcp

✓SAFE B

💻 Give AI models complete control of your computer (probably a bad idea)

★ 3821 readstdio

Run Model Context Protocol (MCP) servers with AWS Lambda

awslabs/run-model-context-protocol-servers-with-aws-lambda

✓SAFE B

Run existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions

★ 3801 readstdio

EVM

mcpdotdirect/evm-mcp-server

✓SAFE B

MCP server that provides LLMs with tools for interacting with EVM networks

★ 3793 writestdio

BloodHound AI

mordavid/bloodhound-mcp-ai

✓SAFE B

BloodHound-MCP-AI is integration that connects BloodHound with AI through Model Context Protocol, allowing security professionals to analyze Active Directory attack paths using natural language instead of complex Cypher queries.

★ 37775 readstdio

Trading Skills

staskh/trading_skills

✓SAFE B

Claude powered advisor system for option traders

★ 3726 write

GPT Researcher

assafelovic/gptr-mcp

✓SAFE B

MCP server for enabling LLM applications to perform deep research via the MCP protocol

★ 3711 writesse

Erick Wendel Contributions

erickwendel/erickwendel-contributions-mcp

✓SAFE B

A Model Context Protocol (MCP) server that provides tools to query Erick Wendel's contributions across different platforms

★ 3675 readstdio

Facebook Ads

gomarble-ai/facebook-ads-mcp-server

✓SAFE B
★ 3664 writestdio

Acemcp

yeuxuan/ace-mcp-node

✓SAFE B

Acemcp 是一个高性能的 MCP (Model Context Protocol) 服务器,专为 AI 助手(如 Claude、GPT 等)提供代码库索引和语义搜索能力。通过 Acemcp,AI 助手可以: 🔍 快速搜索和理解大型代码库 📊 获取带行号的精确代码片段 🤖 自动增量更新索引 🌐 通过 Web 界面管理和调试

★ 3591 readstdio

H1 Brain

patrikfehrenbach/h1-brain

✓SAFE B

MCP server that connects AI assistants to HackerOne for bug bounty hunting

★ 3553 write

Interactive

ttommyth/interactive-mcp

✓SAFE B

Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent

★ 3522 writestdio

Apple Shortcuts

recursechat/mcp-server-apple-shortcuts

✓SAFE B
★ 3511 writestdio

Base

base/base-mcp

✓SAFE B

A Model Context Protocol (MCP) server that provides onchain tools for LLMs, allowing them to interact with the Base network and Coinbase API.

★ 3512 writestdio

Debugger

scriptedalchemy/devtools-debugger-mcp

✓SAFE B

An MCP server exposing full Chrome DevTools Protocol debugging: breakpoints, step/run, call stacks, eval, and source maps.

★ 3507 writestdio

Omnisearch

spences10/mcp-omnisearch

✓SAFE B

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

★ 3503 readstdio

Investor Agent

ferdousbhai/investor-agent

✓SAFE B

A Model Context Protocol server for building an investor agent

★ 3471 writestdio

Linear

jerhadf/linear-mcp-server

✓SAFE B

A server that integrates Linear's project management system with the Model Context Protocol (MCP) to allow LLMs to interact with Linear.

★ 3473 writestdio

Codemogger

glommer/codemogger

✓SAFE B

Codemogger is a code indexing library and MCP server for AI coding agents

★ 3453 readstdio

OnionClaw

christinminor459/onionclaw

!CAUTION B

Provide AI agents with full Tor network access and dark web data through a zero-config OpenClaw skill or standalone tool.

★ 3411 write

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.