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/9

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

193–216 of 3,145 · ranked by trust score, then stars

o3 Search

yoshiko-pg/o3-search-mcp

✓SAFE B

MCP server for OpenAI o3 web search

★ 2861 readstdio

Box CLI

box/boxcli

✓SAFE B

A command line interface for interacting with the Box API.

★ 2851 write

Mongo

kiliczsh/mcp-mongo-server

!CAUTION B

A Model Context Protocol Server for MongoDB

★ 2815 write

Google Search Console

ahonn/mcp-server-gsc

✓SAFE B

A Model Context Protocol (MCP) server providing access to Google Search Console

★ 2771 writestdio

WeChat

biboyqg/wechat-mcp

✓SAFE B

WeChat-MCP: let Openclaw/Claude/ChatGPT and other AI assistants read and reply to WeChat for you

★ 2722 writesse

mcp-trends-hub

baranwang/mcp-trends-hub

✓SAFE B

基于 Model Context Protocol (MCP) 协议的全网热点趋势一站式聚合服务

★ 27121 readstdio

OSP Marketing Tools

open-strategy-partners/osp_marketing_tools

✓SAFE B

A Model Context Protocol (MCP) server that empowers LLMs to use some of Open Srategy Partners' core writing and product marketing techniques.

★ 2706 read

ECharts

hustcc/mcp-echarts

✓SAFE B

🧬 Generate visual charts using ECharts with AI MCP dynamically, used for chart generation and data analysis.

★ 26916 readsse

Trends Hub

baranwang/mcp-trends-hub

✓SAFE B

基于 Model Context Protocol (MCP) 协议的全网热点趋势一站式聚合服务

★ 26921 readstdio

Hwp

jkf87/hwp-mcp

✓SAFE B

mcp for handling hwp

★ 2689 writestdio

Maigret

burtthecoder/mcp-maigret

✓SAFE B

MCP server for maigret, a powerful OSINT tool that collects user account information from various public sources.

★ 2672 readstdio

Gemini

aliargun/mcp-server-gemini

✓SAFE B

MCP server implementation for Google's Gemini API

★ 26117 read

PyScrappy

mldsveda/pyscrappy

✓SAFE B

Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-fingerprint stealth to bypass anti-bot filters, CSS/XPath parsing, and 24 built-in scrapers, clean, structured, LLM-ready data from any URL.

★ 2601 writesse

Seo

cnych/seo-mcp

✓SAFE B

A free SEO tool MCP (Model Control Protocol) service based on Ahrefs data. Includes features such as backlinks, keyword ideas, and more.

★ 2604 read

Easy AutoCAD

zh19980811/easy-mcp-autocad

✓SAFE B

这个项目是一个基于Model Context Protocol (MCP)的AutoCAD集成服务器,它允许通过自然语言与AutoCAD进行交互。通过这个服务器,用户可以使用Claude等大型语言模型来创建、修改和分析AutoCAD图纸,同时还可以存储和查询CAD元素的相关数据。目前制作参考学习,仅实现端到端之间的通信,具体工具函数尚未晚上

★ 2574 write

Suppr

wilddatax/suppr-mcp

✓SAFE B

超能文献|AI驱动的文档翻译与学术搜索服务。支持PDF、DOCX、PPTX等多格式文档的高质量翻译(支持11种语言),特别优化了数学公式翻译。同时提供PubMed学术文献智能搜索功能。更多访问:https://suppr.wilddata.cn

★ 2561 writestdio

Zabbix

mpeirone/zabbix-mcp-server

✓SAFE B

🔌 Complete MCP server for Zabbix integration — Connect AI assistants to Zabbix monitoring with a single unified tool covering 100% of Zabbix APIs. Includes read-only mode and documentation tools for seamless exploration of hosts, items, triggers, templates, problems, and more.

★ 2562 readstreamable-http

Aipolabs

aipotheosis-labs/aipolabs-mcp

✓SAFE B

MCP server(s) for Aipolabs ACI.dev

★ 2521 readstdio

Mcp Chatbot

keli-wen/mcp_chatbot

✓SAFE B

A chatbot implementation compatible with MCP (terminal / streamlit supported)

★ 2511 write

External Application Launcher

andy-portmen/external-application-button

!CAUTION B

Communicate with external applications of your OS through a toolbar button or context menu item.

★ 2481 write

LangChain.js MCP Adapters

langchain-ai/langchainjs-mcp-adapters

✓SAFE B

** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters ** Adapters for integrating Model Context Protocol (MCP) tools with LangChain.js applications, supporting both stdio and SSE transports.

★ 2481 writesse

Scholar Search

silung/scholar-search-mcp

✓SAFE B

An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.

★ 2488 readstdio

Prompt Server

gdli6177/mcp-prompt-server

✓SAFE B

这是一个基于Model Context Protocol (MCP)的服务器,用于根据用户任务需求提供预设的prompt模板,帮助Cline/Cursor/Windsurf...更高效地执行各种任务。服务器将预设的prompt作为工具(tools)返回,以便在Cursor和Windsurf等编辑器中更好地使用。

★ 2472 readstdio

Redmine

runekaagaard/mcp-redmine

!CAUTION B

A redmine MCP server covering close to 100% of redmines API

★ 2461 writestdio

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.