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.
Cite
Cite this page
ModelsAtlas. “MCP servers with no destructive tools”. Retrieved 30 Oct 2026. https://modelsatlas.com/mcp/no-destructive/page/65
Verdicts · 3,151 servers
Transports
- stdio, runs locally2,195
- Streamable HTTP, remote1,064
- SSE, legacy remote253
- Not declared563
A server can list more than one transport.
Alysiadeceptive64/aemet-client
Access Spanish weather data through a TypeScript SDK and Model Context Protocol server for the AEMET OpenData API.
SEOSiri-Official/aeo-geo-mcp
A sovereign, local-first MCP server for AI Engine Optimization (AEO), Generative Engine Optimization (GEO), llm.txt auditing, and content stickiness analytics.
ZekeVoigt/agent-lab
How do AI agents find the web? A live research site: llms.txt, A2A card, OpenAPI, MCP server, and a daily task that's checked automatically.
saviodamato/agentrank-mcp
Find real, verifiable businesses with provenance and source URLs - for AI agents.
menaker/adtest-mcp
MCP server for AdTest.AI: score image, video or text ads with a 13-dimension AI analysis inside Claude and other MCP clients
Autonomad1/computeback-mcp
MCP server for Computeback — the Agent Rewards Marketplace + CB Hire B2B labor (paid in $NOMD on Base L2). Public source mirror of the npm package @autonomad1/computeback-mcp.
aimentiontracker/mcp
MCP server for AIMentionTracker — let Claude, Cursor and other MCP clients read how often ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews name and cite your brand
aioproductos/claude-plugin
Official AIOProductOS plugin for Claude Code — connect your workspace (39 MCP tools) and run evidence-backed weekly product triage
mateuszingano/airlock-rls-mcp
MCP server: let Cursor / Claude Code check a Supabase app for an exposed service_role key and broken RLS while it builds it
thenavidm/apple-podcasts-mcp-cli
Apple Podcasts MCP server and CLI for Claude Code, Codex and AI agents. 32 tools for podcast search, chart rank tracking, listener reviews, RSS feed parsing and validation, on-device transcript search, and Apple Podcasts Connect analytics.
arxivsub/arxivsub-mcp
arxivsub-mcp helps you find papers on arXivSub effortlessly
auten-ai/auten-mcp
Computer use MCP server: give Claude Code, Codex, Cursor or any MCP client hands on your Mac, Windows or Linux desktop.
retracn/automationnation-mcp
MCP server for AI agents: Google Flights, Hotels, Shopping, News, Images, Videos, Jobs, Trends, Maps leads, Ads Transparency, YouTube transcripts, app reviews and AI visibility, via Apify.
SEOSiri-Official/biopharma-mcp
An open-source, local-first Model Context Protocol (MCP) server written in TypeScript for **Biopharma Software Infrastructure, FDA 21 CFR Part 11 GxP Audit Trailing, CDISC SDTM/Allotrope Data Exports, 4PL Dose-Response Curve Fitting, and HIPAA PII/PHI Redaction**.
SEOSiri-Official/biorobotics
An open-source, stateless Model Context Protocol (MCP) framework bridging biological datasets (NCBI/UniProt) with deterministic physical coordinates for robotic automation.
bitmacrocode/charm-mcp
MCP server: authoritative OEM automotive repair data (part numbers, torque specs, procedures) for 1982-2013 vehicles, from factory service manuals. Built for AI agents.
0308ya9392/bubble-agent-mcp
Find emerging conversations before they blow up. An MCP server that brings live Bubble Agent trend intelligence to Claude, Codex, Cursor, and more.
Ambuj123-lab/career-workspace-ambujsystems
Evidence-Grounded Career Workspace & Claim-Validation Engine • Real-Time Company Intelligence • 0% Overclaim Guarantee
All-zzz/claude-canvas
🖥️ Spawn interactive terminal interfaces for emails, calendars, and more with Claude Canvas, a TUI toolkit designed for Claude Code.
Vleickzs/claude-conf
Streamline Claude Code with a modular config toolkit for faster, cleaner terminal workflows
erikhuang76821/code-recall
Local decision ledger for AI coding agents — keeps why a choice was made and which paths are dead ends, and re-injects it after context compaction. Plain Markdown, zero dependencies, works across Claude Code / Codex / Cursor / Copilot / Gemini.
apodal-cherry334/code-review-graph
Map code reviews as graphs to optimize token usage and improve analysis accuracy.
cmgoffena13/codeparse
Give agents fast, accurate, and compact context on your Python codebases
Cdplayerjumpingoffplace65/compass-mcp
Sync Claude Chat, Cowork, and Code with an MCP server that shares tasks, context, and project state across all three.
Other risk hubs
By job
Questions
What counts as destructive?
How is this different from read-only?
Does no destructive tools mean safe?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What counts as destructive?
- How is this different from read-only?
- Does no destructive tools mean safe?