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/112

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

2,665–2,688 of 3,145 · ranked by trust score, then stars

GitHits

githits-com/githits-cli

✕BLOCK F

CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents

★ 1141 writestdio

Cynical Sally

w1ckedxt/cynical-sally

✕BLOCK F

Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.

★ 968 readstdio

TAM

gvaibhav/tam-mcp-server

✕BLOCK F

A comprehensive Model Context Protocol (MCP) server for market sizing analysis, TAM/SAM calculations, and industry research. Built with TypeScript, Express.js, and following the MCP specification.

★ 3668 readsse

Comfy Cozy

josephoibrahim/comfy-cozy

✕BLOCK F

Say 'dreamier' and your ComfyUI workflow shifts — instantly, reversibly. An AI co-pilot for VFX artists: zero-LLM recipes (dreamier/sharper/faster), 133 MCP tools, EXR-aware vision, workflow.lock provenance, full undo, native sidebar, 5 swappable brains (Claude, GPT, Gemini, Ollama, Nemotron).

★ 252 readstdio

mcp-web-validator

AKzar1el/mcp-web-validator

✕BLOCK F

W3C HTML/CSS Validator and Technical SEO Audit MCP Server. Part of the DigestSEO (https://digestseo.com) suite.

★ 98 readstdio

skgate

helv-io/skgate

✕BLOCK F

Any MCP server. Anywhere. An OAuth-protected MCP gateway that can also run the servers, plus SI provider proxying with model aliases, and your Grok subscription as an OpenAI-compatible API with no API key.

★ 91 readstreamable-http

wallet-to-social

starl3xx/wallet-to-social

!CAUTION F

walletlink.social: resolve EVM wallet addresses to the X and Farcaster accounts their owners published, and resolve a handle back to its wallets. REST API, MCP server and an x402 rail, across eight onchain networks.

★ 11 writestreamable-http

@mrrlin-dev/external-agents — Multi-LLM MCP Server

mrrlin-dev/external-agents

✕BLOCK F

One MCP server routes LLM calls across 20+ providers, using round-robin dispatch and fallback to reduce rate-limit interruptions and cut costs up to 100x.

★ 03 writestdio

Stata

hanlulong/stata-mcp

✕BLOCK F

Stata MCP Extension for VS Code, Cursor, and Antigravity IDE

★ 5001 writestreamable-http

db-mcp-server

FreePeak/db-mcp-server

✕BLOCK F

A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.

★ 4612 writestreamable-http

Databricks AI Bridge library

databricks/databricks-ai-bridge

!CAUTION F
★ 1122 writestreamable-http

pi-code

ilovepixelart/pi-code

✕BLOCK F

Claude Code experience for the pi coding agent: reads your .claude config (rules, commands, skills, hooks, output styles, MCP, agents) and adds todo, checkpoints, memory, web search, and subagents.

★ 342 writestdio

GH

veoery/gh_mcp_server

✕BLOCK F

This is a MCP Server that allows LLM to interact with Rhino and Grasshopper directly.

★ 326 write

Social Media

tayler-id/social-media-mcp

✕BLOCK F

A Model Context Protocol (MCP) server that connects to multiple social media platforms

★ 231 writestdio

ctxlint

YawLabs/ctxlint

✕BLOCK F

Lint your AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your codebase

★ 111 writestdio

agenda-intelligence-md

vassiliylakhonin/agenda-intelligence-md

✕BLOCK F

Deterministic evidence-packet checks for AI-generated claims: references, quotes, numbers, and support gaps. CLI, Python, MCP, and review adapters.

★ 817 readstdio

dead-letter

BigCactusLabs/dead-letter

✕BLOCK F

Convert .eml email exports to Markdown with YAML front matter

★ 85 readstdio

gatherthread

TH060419/gatherthread

✕BLOCK F

GatherThread 共序:本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Harness plugin.

★ 61 read

xgen-dex-cli

PlateerLab/xgen-dex-core

✕BLOCK F

XGEN Dex — 데스크톱 · CLI · VSCode 확장이 하나의 코어를 공유하는 저장소

★ 210 readstdio

ozc

joemekw-code/ozc

!CAUTION F

Your AI's trust filter, owned by you. Rate any URL, filter your AI's sources, build transparent information markets. MCP server + REST API + Python SDK.

★ 12 writestdio

social-flow

ttalkkaklab/social-flow

✕BLOCK F

Claude Code plugin: a channel-based short-form/long-form social content pipeline — storyboard with adversarial quality gates, video production, HITL-approved publishing, and autonomous growth loops. Built-in MCP server, 46 tools.

★ 11 writestdio

a0

Joe-Simo/a0

✕BLOCK F

A0: the programming language built for AI, not for people. Compiler in TypeScript; programs compile to native code, wasm, JVM, .NET, Metal, and SystemVerilog.

★ 03 writestdio

Devframe

devframes/devframe

✕BLOCK F

Framework-neutral foundation for building generic DevTools.

★ 6481 writestdio

Hookdeck

hookdeck/hookdeck-cli

✕BLOCK F

CLI for Hookdeck: forward webhooks to localhost (ngrok alternative), manage and query Event Gateway resources (sources, connections, destinations, events), run the MCP server for AI agents. Free for dev.

★ 3641 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.