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/113

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

2,689–2,712 of 3,145 · ranked by trust score, then stars

Russian Marketplace Data

vladimir-human/ru-marketplace-mcp

✕BLOCK F

Одиннадцать маркетплейсов и недвижимость Циан как MCP-серверы: Wildberries, Ozon, Яндекс Маркет, Детский мир, Авито, AliExpress, Taobao, Мегамаркет, Lamoda, DNS, Ситилинк, Циан. Плюс сравнение цен по всем товарным источникам одним вызовом. Только чтение, ключи не нужны.

★ 1361 readstdio

ru-marketplace-mcp

Vladimir-Human/ru-marketplace-mcp

✕BLOCK F

Одиннадцать маркетплейсов и недвижимость Циан как MCP-серверы: Wildberries, Ozon, Яндекс Маркет, Детский мир, Авито, AliExpress, Taobao, Мегамаркет, Lamoda, DNS, Ситилинк, Циан. Плюс сравнение цен по всем товарным источникам одним вызовом. Только чтение, ключи не нужны.

★ 1321 readstdio

Discord

cappyeo/discord-mcp

✕BLOCK F

Open-source Discord MCP server for Claude, Codex, Cursor and other AI clients: 209 typed tools, caller-owned bots, safety controls and verifiable guild builds.

★ 1229 writestdio

VibeCraft

amenti-labs/vibecraft

✕BLOCK F

AI-driven vibe based Minecraft building via MCP. Describe a build, watch your agent construct it in Minecraft.

★ 10145 readstdio

PrimeUIX

primefaces/primeuix

✕BLOCK F

PrimeUIX is a shared package used by all Prime libraries, allowing PrimeTek teams to unify theming.

★ 941 writestdio

CodingBaby Browser

buyitsydney/codingbaby-browser-mcp

✕BLOCK F

MCP Server allowing AI agents to control Google Chrome via the CodingBaby Extension

★ 293 writestdio

cmuxlayer

EtanHey/cmuxlayer

✕BLOCK F

10 public MCP tools for controlling cmux workspaces and managing Claude, Codex, Gemini, Kiro, and Cursor agents.

★ 282 writestdio

FylloCode

fioooooooo/fyllocode

✕BLOCK F

FylloCode 是一个开源桌面应用,把 Claude Code、Codex 等本地 Coding Agent 接进项目工作流。派任务、审方案、追溯每一次改动,积累下来的规范和结论,换一个 Agent 也能继承。

★ 284 writestdio

AI-Native Open-source Casino Platform Framework

blurifycom/openora

✕BLOCK F

Open-source Casino Platform Framework - AI-Native, Self-hosted, Headless, Plugin-based 🎰

★ 252 writestdio

tianshu-mcp

lanlan0811/tianshu-mcp

✕BLOCK F

天枢harness × AI-Agent 编排 MCP server:调度外部 Agent 干活,用运行时证据做客观验收,不通过自动返修闭环。

★ 107 readstdio

aiterm-mcp

kitepon/aiterm-mcp

✕BLOCK F

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

★ 61 writestdio

fluent-ui-plugin

ArasaniRohithReddy/fluent-ui-plugin

✕BLOCK F

Agents, skills and MCP tools to build and adopt Microsoft Fluent 2 (Fluent UI 2.0) across Web, native iOS/Android/Windows, Power BI and Power Platform - plus Fluent 1 (v8) support, v8-to-v9 migration and Figma. Works in Copilot CLI, VS Code, Cursor, Claude, Gemini and more.

★ 12 writestdio

WEALTH

ariffazil/WEALTH

✕BLOCK F

Capital intelligence: risk, NPV, markets. Research and evidence only. Never moves money.

★ 16 writesse

designesy-org

LE-VAI/designesy-org

!CAUTION F

Scores any URL against a 44-check design contract (A-F grade), validates DTCG tokens, and checks drift and AI readiness.

★ 018 readstdio

rolling-design-sync

deven-bryant/rolling-design-sync

✕BLOCK F

Per-node design-implementation ledger: a Figma plugin, API, and agent tooling that tell coding agents exactly which design changes aren't built yet.

★ 01 writestdio

tw-market-live-data-intelligence

SmartyJohnway/tw-market-live-data-intelligence

✕BLOCK F

Local-first Taiwan market evidence workbench for AI agents — TWSE/TPEx, persistent Watchlists, governed MCP, auditable evidence, explicit execute-once.

★ 01 readstdio

Open Multi Agent

open-multi-agent/open-multi-agent

✕BLOCK F

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

★ 6,9978 writestreamable-http

Deep Research

u14app/deep-research

✕BLOCK F

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

★ 4,6892 writesse

fastCRW

fastcrw/crw

✕BLOCK F

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma

★ 1,1141 readstdio

Unreal Editor

db-lyon/ue-mcp

✕BLOCK F

Complete Unreal Engine development toolkit exposed as MCP tools.

★ 3824 readstdio

AutoPentest

bhavsec/autopentest-ai

✕BLOCK F

Agentic Pentesting MCP server that discovers, exploits, and reports web application vulnerabilities.

★ 23212 writestdio

www-project-agent-memory-guard

OWASP/www-project-agent-memory-guard

✕BLOCK F

OWASP Foundation web repository

★ 1835 readstdio

Vnsh

raullenchai/vnsh

✕BLOCK F

One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.

★ 1574 writestdio

Reshapr

reshaprio/reshapr

✕BLOCK F

The open source, no-code MCP Server for AI-Native API Access

★ 1282 read

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.