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/123
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
2,929–2,952 of 3,145 · ranked by trust score, then stars
Drift
dadbodgeoff/drift
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
EDT-MCP
DitriXNew/EDT-MCP
MCP for 1C:EDT
EDT
ditrixnew/edt-mcp
MCP for 1C:EDT
JSON Server
gongrzhe/json-mcp-server
JSON handling and processing mcp server
Workflows
dx-zero/mcpn
orchestrate & combine prompts + MCP servers into compound MCP tools
Fast Telegram
leshchenko1979/fast-mcp-telegram
Telegram MCP gateway for AI agents: 8 tools, multi-tenant HTTP/stdio, MTProto
crazyrabbitltc/mcp-twitter-server
Model Context Protocol Server for Accessing twitter
artifactflow
Gadsotek/artifactflow
Open-source, self-hosted, versioned vault for AI-generated HTML, Markdown, Mermaid, and image artifacts, with scoped MCP access and isolated two-origin previews.
runtime
withruntime/runtime
Sandboxes for AI agents: TypeScript, Python, Go, Java and Ruby SDKs, the runtime CLI, an MCP server, and agent integrations. Firecracker microVMs.
Kybernesis Platform
KybernesisAI/platform
lense
adeelahmad/lense
Lens: intelligence for your agent. Safe, secure and cost-effective. A self-hosted, cited knowledge graph and MCP server for your agents, from a Raspberry Pi to the cloud.
Chrome Browser
hangwin/mcp-chrome
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
kubernetes-mcp-server
containers/kubernetes-mcp-server
Model Context Protocol (MCP) server for Kubernetes and OpenShift
HOL Standards SDK
hashgraph-online/standards-sdk
The official HOL Standards SDK, implementing the standards found in https://hol.org/docs/standards
Octocode
bgauryy/octocode-mcp
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
codflow
bighadj22/codflow
The open-source, COD-first e-commerce + delivery platform for Algeria built agentic-ready.
Sage
l33tdawg/sage
(S)AGE - (Sovereign) Agent Governed Experience
Axon
ali-kamali/axon.mcp.server
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants
llm-router
ypollak2/llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
gitlab-mcp-server
jmrplens/gitlab-mcp-server
Open source GitLab MCP server for AI assistants: 2-tool dynamic find/execute over 850+ GitLab actions (1,000+ Enterprise), stdio/HTTP/OAuth, safe/read-only modes.
engram
the-long-ride/engram
Engram - file-system-based memory management system for AI agents that grows with you & your teams, across agents, projects, and devices.
deepPairing
mitchjablonski/deepPairing
Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.
living-bread-mcp
thegoodfruit/living-bread-mcp
Remote MCP server for The Living Bread: Scripture from a stored text, verses for a need, real churches and gatherings, and the prayers real people prayed over you. mcp.living-bread.org
PhpMyFAQ
thorsten/phpmyfaq
phpMyFAQ - Open Source FAQ web application for PHP 8.4+ and MySQL, PostgreSQL and other databases
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?