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/128

Verdicts · 3,145 servers

✓SAFE1,632!CAUTION521✕BLOCK992

Transports

A server can list more than one transport.

3,145 servers

3,049–3,072 of 3,145 · ranked by trust score, then stars

Flexible GraphRAG

stevereiner/flexible-graphrag

✕BLOCK F

Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch DBs. 14 data sources, 10 auto sync: Alfresco, Nuxeo, etc. KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends

★ 1889 read

AI for the Win

depalmar/ai_for_the_win

✕BLOCK F

Build AI-powered security tools. 50+ hands-on labs covering ML, LLMs, RAG, threat detection, DFIR, and red teaming. Includes Colab notebooks, Docker environment, and CTF challenges.

★ 1631 writestdio

Origin

7xuanlu/origin

✕BLOCK F

A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.

★ 7917 readstreamable-http

Wenlan

7xuanlu/wenlan

✕BLOCK F

A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.

★ 7917 readstreamable-http

Mythos Agent

mythos-agent/mythos-agent

✕BLOCK F

The AI security agent guards your code.

★ 4419 readstdio

Whetstone

iliaal/whetstone

✕BLOCK F

AI-powered development tools. 18 agents, 19 commands, 29 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

★ 362 write

BuildersGate

Thepizzapie/BuildersGate

✕BLOCK F

Agentic game development for building games with AI Agents. Run one session per seat: art, gameplay, narrative, QA, audio, tech all in 1 spot

★ 294 write

corpusiq-docs

CorpusIQ/corpusiq-docs

✕BLOCK F

Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patterns. Production-tested from 1,200+ hours of ops. Updated daily.

★ 232 read

kodelyth-ecc

sifxprime/kodelyth-ecc

✕BLOCK F

70 agents · 196 skills · 103 commands · 44 hook entries · semantic intent routing · self-learning memory · GOD vs EVIL arena · MCP server. macOS, Linux and Windows. Claude Code, Windsurf, Cursor, Codex, Antigravity, Cline, Roo Code, Aider, Kimi, Gemini CLI. MIT.

★ 1122 readstdio

aziel-runtime

AzielEliab/aziel-runtime

✕BLOCK F

Aziel Runtime by Aziel Eliab — FragGate MCP Softwares door. https://aziel-runtime.vibelock.workers.dev/ · OpenAPI+MCP · Glama · hubs azieleliab.com · corpus · godlock.uk · HDJ.

★ 22 writestreamable-http

feedback-kit-skills

tianhaoz95/feedback-kit

✕BLOCK F

Turn in-app user feedback into agent-ready coding prompts.

★ 12 writestdio

Selene

tercumantanumut/selene

✕BLOCK F

Selene is a desktop app that runs AI agents on your machine. Connect them to your WhatsApp, Telegram, Slack, or Discord. Write code, generate images, build personal assistants. All from one place. Your data stays on your device.

★ 1692 writestreamable-http

Seline

tercumantanumut/seline

✕BLOCK F

Selene is a desktop app that runs AI agents on your machine. Connect them to your WhatsApp, Telegram, Slack, or Discord. Write code, generate images, build personal assistants. All from one place. Your data stays on your device.

★ 1692 writestreamable-http

Open Computer Use

wide-moat/open-computer-use

✕BLOCK F

ARCHIVED — superseded by Wide Moat

★ 1261 writestreamable-http

elixir-mcp

jthingelstad/elixir-mcp

✕BLOCK F

Clash Royale history recorder + remote MCP server. Unofficial; not endorsed by Supercell.

★ 14 write

Receiz-commerce

kojibai/Receiz-commerce

✕BLOCK F

Open-source, no-code ecommerce launcher and developer kernel for proof-native artifacts. Clone, configure, and launch your own storefront powered by the Receiz SDK, MCP server, offline verification, ownership receipts, and programmable commerce objects.

★ 14 read

anysearch-cli

Xxx91n/anysearch-cli

✕BLOCK F

Vertical-domain information-specialist agent CLI — search + research + memory + knowledge with domain allowlists, abstain-first answers, and a fail-open MCP server

★ 01 writestdio

mcp-agentgate

wookat/agentgate

✕BLOCK F

AgentGate — scan, lock, and gate your MCP servers. npm-audit + lockfile + CI drift gate for the MCP era.

★ 06 writesse

Ouroboros

q00/ouroboros

✕BLOCK F

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

★ 6,0503 readsse

Notte

nottelabs/notte

✕BLOCK F

Cloud browser infrastructure and web automation platform for your AI and coding agents

★ 2,0022 readstreamable-http

unifi-mcp

sirkirby/unifi-mcp

✕BLOCK F

MCP servers & Graph API for the UniFi suite of applications, Network, Protect, and Access

★ 8727 writesse

UniFi Network

sirkirby/unifi-network-mcp

✕BLOCK F

MCP servers & Graph API for the UniFi suite of applications, Network, Protect, and Access

★ 8697 writesse

UniFi Network

sirkirby/unifi-mcp

✕BLOCK F

MCP servers & Graph API for the UniFi suite of applications, Network, Protect, and Access

★ 8537 writesse

IJFW

therealseandonahoe/ijfw

✕BLOCK F

IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.

★ 2122 write

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.