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/109
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
2,593–2,616 of 3,145 · ranked by trust score, then stars
agentigris-agentfund
agentigris/agentfund
Fundraising infrastructure for AI agents on Solana — x402 payments, milestone escrow, on-chain reputation. REST + WebSocket + MCP + ACP.
MapSmith
mapsmith-ai/MapSmith
Professional-grade GIS geoprocessing over MCP, with a verifiable provenance manifest on every output
mcp-core
n24q02m/mcp-core
Shared foundation for building MCP servers -- Streamable HTTP transport, OAuth 2.1, browser-based credential setup, and a shared embedding daemon.
claude-grok-build-plugin
xzawed/claude-grok-build-plugin
A Claude Code plugin (MCP-server wrapper) that lets Claude delegate coding tasks to xAI's Grok Build CLI — billed via your xAI subscription, not metered API. 9 MCP tools, /grok:* commands.
noted
fabriziosalmi/noted
Desktop app for taking notes in Markdown/HTML, with built-in AI, note links (wikilinks), global search, local history, and Git integration
Jentrix open client
jentrix-au/jentrix
Jentrix open client: the CLI and the official Claude Code and Codex plugins
omneum
cole-h06/omneum
An open-source context evaluator for AI agents.
open-task-relay-public
lanekingsbery/open-task-relay-public
Open-source task commons where AI agents do bounded public-good work, publish evidence, and review results.
Doris
apache/doris-mcp-server
Apache Doris MCP Server
ClaudeR
imnmv/clauder
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
AWR
originoneai/awr
Persistent work state and minimal context for long-running AI agents.
Transloadit Node.js SDK
transloadit/node-sdk
Transloadit's official Node.js SDK
W&B
wandb/wandb-mcp-server
The official implementation of the W&B Models and Weave MCP server.
OmniMesh Gateway
omnimesh-labs/omnimesh-gateway
Model Context Protocol (MCP) Gateway & Registry - Central hub for managing tools, resources, and prompts for MCP-compatible LLMs. Translates REST APIs into MCP, builds virtual MCP servers with security and observability, and bridges multiple transports (stdio, SSE, streamable HTTP).
Puppeteer Real Browser
withlinda/puppeteer-real-browser-mcp-server
Provides AI assistants with powerful, detection-resistant browser automation capabilities built on ZFC Digital's puppeteer-real-browser package.
@waniwani/sdk
WaniWani-AI/sdk
Build distribution MCPs: multi-step conversational funnels (lead gen, booking, quotes) that run as a single MCP tool in ChatGPT, Claude, and Cursor. A typed state graph compiles to one MCP tool.
yorishiro-proxy
usk6666/yorishiro-proxy
AI-native MITM proxy — MCP server for traffic interception, recording & replay
MCPg
devopam/MCPg
Postgres MCP Server
career-compass-mcp
benskamps/career-compass-mcp
Turn Claude into a full job-search partner — Career KB, tailored resumes, application pipeline, interview prep. MCP server + local dashboard; your data never leaves your machine.
expense
assaf/expense
Forward a receipt to your inbox and it's filed automatically.
mcp-server
pipeshub-ai/mcp-server
This repository contains the packages that make up Pipeshub’s local MCP server
open-memex
stoneskin/open-memex
Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs.
orbit-vsx
oaslananka/orbit-vsx
VS Code extension for MCP health, debug-session intelligence, and A2A trust workflows: monitor companion services, inspect Agent Cards, enforce workspace trust, and expose bounded tools to agent mode.
dibs
Agenxy/dibs
Keeps your agents in the loop about each other. See what the fleet is doing, then message, sync and send files between agents. Dibs reports; it never acts.
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?