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.
Cite
Cite this page
ModelsAtlas. “MCP servers with no destructive tools”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/no-destructive/page/101
Verdicts · 3,145 servers
Transports
- stdio, runs locally2,191
- Streamable HTTP, remote1,060
- SSE, legacy remote253
- Not declared563
A server can list more than one transport.
3,145 servers
2,401–2,424 of 3,145 · ranked by trust score, then stars
memex
STiFLeR7/memex
Persistent memory for AI coding agents via MCP: a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter and Gemini Flash into Neo4j via Graphiti. 14 MCP tools, hierarchical clusters, three-regime confidence decay.
lain
spuentesp/lain
High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust.
mcp-server
Coinversaa/mcp-server
Hyperliquid trading intelligence for AI agents — 106 available MCP tools: builder analytics (revenue, retention, audience overlap, user journey), cohort analytics, position lifecycles, liquidation heatmaps, trader profiling, HIP-4 outcome contracts, and live market data. Hosted connector at mcp.coin
warden-ai
rynald0cst0ltziam/Warden-AI
The structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.
aura
trotor/aura
Suomalaisen avoimen datan discovery- ja ymmärryspalvelu — MCP-server tekoälyille, avoin web-palvelu ihmisille
agent-discover
keshrath/agent-discover
MCP server registry and marketplace — discover, install, activate, and manage MCP tools on demand
aikstockdata
na77tech-creator/aikstockdata
Korean stock data for AI: KOSPI/KOSDAQ/KONEX closes, DART disclosures with receipt time, post-filing price paths. JSON + remote MCP server, no API key.
Epoch
KyaniteLabs/Epoch
Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time mapping, cost estimation, and schedule risk tools.
arr-mcp
Knuckles-Team/arr-mcp
Arr related MCP and A2A / AG-UI Agent
blender-mcp
Vertiiii/blender-mcp
🛠️ Connect Blender to Claude AI for seamless 3D modeling and scene manipulation using the Model Context Protocol for enhanced creative workflows.
decisions-judge-mcp
clouatre-labs/decisions-judge-mcp
Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.
EPICS-MCP
epicDirk/EPICS-MCP
Ask an AI assistant about your EPICS control system: live PV values, why a PV is disconnected, and where it appears across ChannelFinder, the Archiver and the alarm tree. Read-only by default.
sandrone
kuuvahki-labs/sandrone
Self-hosted proxy configuration workbench for aggregating subscriptions, probing nodes, and generating Mihomo, sing-box, and Shadowrocket configs.
OpenAPI to Tools
buildwithlayer/openapi-to-tools
assemblash
VidGuiCode/assemblash
Local-first visual document engine with a web editor, CLI, API, and MCP server - built for humans and AI agents.
KGraph
ajksunkang-aios/KGraph
The Compiler-Aware Operating System Kernel CodeGraph Engine for Token-Efficient Structural Codebase Retrieval
LibreGene
dl-li/LibreGene
An open-source, agent-ready plasmid editor.
libreoffice-mcp
sandraschi/libreoffice-mcp
LibreOffice headless automation via FastMCP — Writer/Calc/Impress convert, ODT merge, PDF combine, folder watch. For Cursor / Claude Desktop.
pkgtruth
hxckya/pkgtruth
Ground truth about npm packages for AI coding agents. Catches hallucinated and slopsquatted dependencies before they reach your lockfile.
Angular Starter
4sh/starter-angular
An Angular component library that natively integrates your design tokens to create a seamless bridge between design and code.
Neta
sudhanshug16/neta
A leader agent that delegates to tiered worker agents behind the coding-agent CLI you already use — Claude Code, Codex, or OpenCode.
agent-harness-generator
Daffiburrlike452/agent-harness-generator
Create custom AI agent harnesses for any repository using this CLI generator.
audio-transcriber
Knuckles-Team/audio-transcriber
Transcribe audio into text. Agentic AI supported through MCP Server.
cal
Dvorinka/cal
Self-hosted daily toolkit — calendar, tasks, notes, links, files, kanban boards, time tracking, GitHub inbox. One Docker container.
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?