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/110
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
2,617–2,640 of 3,145 · ranked by trust score, then stars
agentic-coding-harness
sblattj/agentic-coding-harness
Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.
Blender Model Context Protocol
ahujasid/blender-mcp
Community plugin to control Blender 3D with any LLM of your choice
Reverse Engineer Anything
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Iai
codeabra/iai-mcp
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
Avrotize
clemensv/avrotize
Avrotize is a command-line tool for converting data structure definitions between different schema formats, using Apache Avro Schema as the integration schema model.
USolver
sdiehl/usolver
A model context protocol server for solving combinatorial optimization problems with logical and numerical constraints.
Keryx
actionhero/keryx
Keryx: The Fullstack TypeScript Framework for MCP and APIs
Kindex
jmcentire/kindex
Knowledge index that learns from your conversations
lockstep
lockstep-team-agent/lockstep
Keep your team's AI coding agents coordinated — without sharing source code.
memtomem-stm
memtomem/memtomem-stm
Short-term memory proxy gateway with proactive memory surfacing for AI agents
WebPieces TypeScript
deanhiller/webpieces-ts
obsidian-llm-wiki
Statutecontempt951/obsidian-llm-wiki
Convert your Obsidian markdown vault into a six-persona MCP team for local LLM tools to provide cited, accurate insights.
assetfare-mcp
assetfare/assetfare-mcp
USDC bridge API for AI agents and agent-wallet funding: Solana to Base + 76 routes; validated provider paths; exact 1bp; server never signs/submits.
vetagent
jakegu1/vetagent
VetAgent — token risk intelligence MCP for AI agents. Cloudflare Worker deployment. Assess token risk (liquidity/honeypot/rug) and return actionable low/medium/high verdict. Remote MCP at https://vetagent.dev/mcp.
ztrack
volter-ai/ztrack
ztrack: evidence-gated task tracking for AI agents
Memlab
facebook/memlab
A framework for finding JavaScript memory leaks and analyzing heap snapshots
Stripe Agent Toolkit
stripe/agent-toolkit
One-stop shop for building AI-powered products and businesses with Stripe.
Solana Agent Kit
sendaifun/solana-agent-kit
connect any ai agents to solana protocols
xmcp
basementstudio/xmcp
The TypeScript MCP framework
sandbase-harness
sandbaseai/sandbase-harness
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
Kuvasz
kuvasz-uptime/kuvasz
Kuvasz (pronounce as [ˈkuvɒs]) is an open-source uptime and SSL monitoring service, with multiple notification channels, status pages, IAC support via YAML, Prometheus integration, a complete REST API and many more!
Salesforce
salesforcecli/mcp
MCP Server for interacting with Salesforce instances
premiere-pro-mcp
leancoderkavy/premiere-pro-mcp
Adobe Premiere Pro MCP — independent, local-first server for supported workflows. Connect Claude, Codex, or Cursor through a local CEP bridge.
Remote PostgreSQL Database
coleam00/remote-mcp-server-with-auth
Template for a remote MCP server with GitHub OAuth - following best practices for building MCP servers so you can take this as a starting point for any MCP server you want to build!
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?