MCP servers · least privilege

MCP servers with no destructive tools

3,151 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. 1,622 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 30 Oct 2026. https://modelsatlas.com/mcp/no-destructive/page/63

Verdicts · 3,151 servers

✓SAFE1,634!CAUTION522✕BLOCK995

Transports

A server can list more than one transport.

3,151 servers · 1,489–1,512 · ranked by trust score, then stars
goaimoat-ai-visibility-mcp!CAUTION B

jayniebingyu-cyber/goaimoat-ai-visibility-mcp

GoAI Moat - AI Visibility Audit MCP server. Diagnose a brand visibility in AI answers (ChatGPT, Perplexity, AI Overviews). https://mcp.goaimoat.com/mcp

★ 1GitHub stars3 readstreamable-http
graphmaxer-gw1✓SAFE B

Graphmaxer/gw1-mcp

GW1 build compiler MCP server: skill data, template code encode/decode, validation, hero roster. Read-only.

★ 1GitHub stars2 readstdio
internet-radio-mcp!CAUTION B

AlonDrilich/internet-radio-mcp

MCP server for internet radio: search 50,000+ stations, get stream URLs, top/trending stations, countries and genres (Radio Browser public-domain data). By 72FM.

★ 1GitHub stars5 readstdio
kazkozdev-abscissa✓SAFE B

KazKozDev/abscissa

A safety-aware MCP server that lets AI agents manage Linear issues, projects, cycles, and dependencies.

★ 1GitHub stars17 readstdio
KYVAutoResearch-v2✓SAFE B

kyvjyf/KYVAutoResearch-v2

Project-based auto-research AI agent framework. Problem × Evidence Matrix, evidence grading, MCP Server. Python 3.10+. | 项目制自动研究 Agent 框架:问题 × 证据矩阵、证据分级。

★ 1GitHub stars15 writestdio
local-terminal-mcp✓SAFE B

luckysolanki902/local-terminal-mcp

Run local commands from ChatGPT or Claude via a safe, allowlisted MCP server. Work on your codebase and generate images/sprites/assets locally from ChatGPT without spending Codex/API tokens. stdio for Claude Desktop/Code; capability-URL or bearer auth over HTTP for ChatGPT via ngrok or cloudflared.

★ 1GitHub stars3 readstdio
machinegrade-validate✓SAFE B

machinegrade/validate

Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL. Typed verdicts with fix hints. Metered API + MCP.

★ 1GitHub stars2 readstdio
market-intelligence-mcp✓SAFE B

BullrunData/market-intelligence-mcp

Market intelligence MCP server for Claude, ChatGPT, Cursor, and any MCP client — recession probability, sector rotation, institutional positioning, macro indicators, and real estate calculators.

★ 1GitHub stars1 writestdio
MCP-Ambari-API✓SAFE B

call518/MCP-Ambari-API

🚀 Natural-language Hadoop cluster management via MCP. Connect LLM agents (Claude, GPT, etc.) directly to Apache Ambari REST API — control services, inspect configs, query metrics, and manage alerts with AI. Built with FastMCP & aiohttp.

★ 1GitHub stars1 readstdio
mcp-atlas✓SAFE B

urbankitstudio/mcp-atlas

MCP server: find a US county's official parcel ArcGIS endpoint and search it by owner name or APN. No API key. npx -y @urbankitstudio/mcp-atlas

★ 1GitHub stars4 readstdio
mcp-marmiton✓SAFE B

smeet666/mcp-marmiton

MCP server for Marmiton: search French recipes and scale ingredient quantities to any number of servings. No API key.

★ 1GitHub stars3 readstdio
mcp-masterclass✓SAFE B

genaiunplugged14/mcp-masterclass

Code and checkpoints for the MCP Masterclass: 4 modules, 30 video lessons, one server (Scribe) built end to end on the MCP Python SDK v2.

★ 1GitHub stars4 writestdio
mcp-sdk-typescript✓SAFE B

Palald/mcp-sdk-typescript

🚀 Build efficient applications with the MCP SDK for TypeScript, offering optimized performance, real-time communication, and robust session management.

★ 1GitHub stars1 writestreamable-http
mcp-server✓SAFE B

SocialAPIsHub/mcp-server

MCP server for Facebook & Instagram data — pages, posts, groups, Ads Library, Marketplace, profiles, reels. 47 read-only tools. npx or hosted at mcp.socialapis.io/mcp

★ 1GitHub stars9 writestdio
mcp-server✓SAFE B

synchronicity-labs/mcp-server

MCP server for the Sync API — give AI agents the ability to create lipsync videos, manage assets, and more

★ 1GitHub stars12 writestdio
mcp-server✓SAFE B

TranscriptFetch/mcp-server

MCP server for TranscriptFetch: transcripts from YouTube, TikTok, Instagram and media URLs, with AI transcription when captions are missing, plus YouTube search, channel and playlist listing, from any MCP client.

★ 1GitHub stars4 readstdio
mcp-server-axiom✓SAFE B

ThetaBird/mcp-server-axiom-js

★ 1GitHub stars3 readstdio
MemAI!CAUTION B

Filipe-Soares-de-Almeida/MemAI

Long-term memory MCP server for AI agents — one ACID SQLite file, FTS5 BM25 retrieval, nested domains, diagrams and a local curation dashboard

★ 1GitHub stars2 read
mohsinmshabbir-datasaudi✓SAFE B

mohsinmshabbir/datasaudi-mcp

Saudi economic data for Claude, Cursor & any MCP client — English or Arabic, keyless. Refuses to silently mislead.

★ 1GitHub stars3 readstdio
moodle-mcp-server✓SAFE B

csmediapro/moodle-mcp-server

Open-source MCP server that connects AI agents to Moodle LMS data through Moodle Web Services.

★ 1GitHub stars8 readstdio
narwhal!CAUTION B

yumingtao/narwhal

A local-first, privacy-first AI agent. Your conversations, projects, and work context stay on your machine.

★ 1GitHub stars1 writestreamable-http
octoparse✓SAFE B

octoparse/octoparse-mcp

Official Octoparse MCP server for AI-powered web scraping workflows.

★ 1GitHub stars1 writestreamable-http
ollama-LLM-agent✓SAFE B

euiyounghwang/ollama-LLM-agent

ollama-LLM-agent

★ 1GitHub stars1 write
opdstar-nhi-mcp✓SAFE B

tatsuju/opdstar-nhi-mcp

Taiwan National Health Insurance (NHI) data for AI agents via Model Context Protocol. Powered by OPDSTAR (https://opdstar.com).

★ 1GitHub stars1 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 (1,622 servers). This list also includes servers whose tools write: 1,529 of the 3,151 do.
Does no destructive tools mean safe?
No. 1,634 are SAFE, 522 CAUTION and 995 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.