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/81

Verdicts · 3,151 servers

✓SAFE1,634!CAUTION522✕BLOCK995

Transports

A server can list more than one transport.

3,151 servers · 1,921–1,944 · ranked by trust score, then stars
Hyades!CAUTION B

apology-is-policy/hyades

Unicode/ASCII Mathematical Typesetting Engine with LaTeX Input, VSCode Integration, MCP server, and Automatic Rendering into Source Code Comments

★ 30GitHub stars2 readstreamable-http
Rollbar!CAUTION B

rollbar/rollbar-mcp-server

Model Context Protocol server for Rollbar

★ 28GitHub stars1 writestdio
CSS Noop Checker!CAUTION B

purupurupu/css-noop-checker

Chrome DevTools extension that detects CSS properties with no effect

★ 25GitHub stars3 readstdio
RTFM!CAUTION B

roomi-fields/rtfm

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

★ 25GitHub stars8 readstdio
dsh-skills-anywhere!CAUTION B

noteflowai/dsh-skills-anywhere

Check Agent Skills before reuse: find missing local resources in browser or CI, review pinned examples, and serve skills through DeepSeek Harness or MCP.

★ 6GitHub stars9 readstdio
lemonsqueezy-mcp!CAUTION B

YawLabs/lemonsqueezy-mcp

LemonSqueezy MCP server for managing your store from AI assistants

★ 4GitHub stars1 writestdio
echelongraph-mcp!CAUTION B

echelongraph/echelongraph-mcp

MCP server for CVE intelligence: 16 read-only tools for CVE records, CISA KEV, EPSS history, exploits, fix guidance as sources state it, version, SBOM and lockfile checks, vendor advisories, and per-CVE exposure from Shodan data (© Shodan). Free and keyless.

★ 2GitHub stars13 readstdio
stop-ai-slop!CAUTION B

WhiteBite/stop-ai-slop

Zero-dependency linter and gate that blocks AI-generated comment slop: multi-line narrative comments, changelog markers, step-numbered filler. Write-time plugin for OpenCode, Claude Code hooks, pre-commit, GitHub Action, GitLab CI, MCP server. RU+EN+DE+FR+ES detection.

★ 2GitHub stars1 write
6F!CAUTION B

Xxx91n/6F

Macro + micro engineering-content audit for git-healthy repositories — Claude Code Agent Plugin (Hub-of-Facts + federated adjudication, evidence gates, verifiable receipts). Preview: 3 of 5 capabilities live.

★ 0GitHub stars1 read
indexagentica-mcp!CAUTION B

Drudley/indexagentica-mcp

Read-only remote MCP server (Streamable HTTP) and REST search for indexagentica.com

★ 0GitHub stars4 readstreamable-http
microsoft-agent✓SAFE B

Knuckles-Team/microsoft-agent

Microsoft A2A / AG-UI Agent

★ 0GitHub stars3 writesse
oszillation-mixing-buddy!CAUTION B

WizardofTryout/oszillation-mixing-buddy

Universal AI Co-Producer for DAWs · Bit-transparent ITU-R BS.1770-4 telemetry, 128-band RTA & zero-latency native accessibility bridges (macOS / Logic Pro & Steinberg).

★ 0GitHub stars10 writesse
Spec Workflow!CAUTION B

pimzino/spec-workflow-mcp

A Model Context Protocol (MCP) server that provides structured spec-driven development workflow tools for AI-assisted software development, featuring a real-time web dashboard and VSCode extension for monitoring and managing your project's progress directly in your development environment.

★ 4,293GitHub stars3 writestdio
Ghidra!CAUTION B

bethington/ghidra-mcp

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.

★ 3,948GitHub stars3 readstdio
Code Interpreter API!CAUTION B

shroominic/codeinterpreter-api

👾 Open source implementation of the ChatGPT Code Interpreter

★ 3,844GitHub stars1 read
Azure DevOps!CAUTION B

microsoft/azure-devops-mcp

The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.

★ 2,027GitHub stars3 readstdio
LLM Wiki!CAUTION B

lucasastorian/llmwiki

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

★ 1,643GitHub stars2 readstreamable-http
Coding Tools!CAUTION B

xytom/coding-tools-mcp

Give any AI agent the ability to code

★ 1,158GitHub stars2 writestdio
Mem0!CAUTION B

mem0ai/mem0-mcp

★ 662GitHub stars1 readstdio
KiCad!CAUTION B

lamaalrajih/kicad-mcp

Model Context Protocol server for KiCad on Mac, Windows, and Linux

★ 525GitHub stars1 write
TrueMemory✓SAFE B

buildingjoshbetter/truememory

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

★ 379GitHub stars1 readstdio
Notion!CAUTION B

awkoy/notion-mcp-server

Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context Protocol — pages, databases, blocks, comments, files.

★ 173GitHub stars1 readstdio
Outline Connector!CAUTION B

vortiago/mcp-outline

A Model Context Protocol (MCP) server enabling AI assistants to interact with Outline documentation services.

★ 156GitHub stars1 readsse
SPARQL-LLM!CAUTION B

sib-swiss/sparql-llm

🦜✨ Chat system, MCP server, and reusable components to improve LLMs capabilities when generating SPARQL queries

★ 127GitHub stars1 writesse

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.