MCP servers · least privilege
Read-only MCP servers
1,620 MCP servers declare tools that only read: none of their tools is classed write or destructive. That makes them the safest place to start giving an agent access. Read-only describes the tools, not the code, so the audit verdict still decides whether to connect one.
Cite
Cite this page
ModelsAtlas. “Read-only MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/read-only/page/53
Verdicts · 1,620 servers
Transports
- stdio, runs locally1,124
- Streamable HTTP, remote555
- SSE, legacy remote133
- Not declared284
A server can list more than one transport.
1,620 servers
1,249–1,272 of 1,620 · ranked by trust score, then stars
Goke
remorses/goke
simple, type safe, elegant command line framework. the CLI framework for agents
CKAN Server
ondata/ckan-mcp-server
MCP server for querying CKAN open data portals (package search, DataStore SQL, organizations, groups, tags)
Context Awesome
bh-rat/context-awesome
awesome-lists now available as CLI & MCP server for your agent.
Contentful
contentful/contentful-mcp-server
MCP (Model Context Protocol) server for the Contentful Management API
Brightspace
rohanmuppa/brightspace-mcp-server
MCP server for Brightspace (D2L). Check grades, due dates, assignments, announcements, rosters, syllabus & course content via Claude, ChatGPT, Cursor, Windsurf, or any MCP client. Works with any school. npm: npx brightspace-mcp-server@latest
brightspace-mcp-server
RohanMuppa/brightspace-mcp-server
MCP server for Brightspace (D2L). Check grades, due dates, assignments, announcements, rosters, syllabus & course content via Claude, ChatGPT, Cursor, Windsurf, or any MCP client. Works with any school. npm: npx brightspace-mcp-server@latest
Cedar For Agents
cedar-policy/cedar-for-agents
Python Local
alec2435/python_mcp
MCP Server to run python code locally
A11y
priyankark/a11y-mcp
An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core. Use the results in an agentic loop with your favorite AI assistants (Amp/Cline/Cursor/GH Copilot) and let them fix a11y issues for you!
Dotbot
andresharpe/dotbot
Structured, auditable AI-assisted development for teams. Zero-dependency MCP server, web dashboard, and multi-provider AI CLI support.
Widget
ref-tools/widget-mcp
Simple MCP-UI widgets for common use cases.
@putervision/state-memory-mcp
putervision/state-memory-mcp
Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.
maintainer-skills-lab
00200200/maintainer-skills-lab
17 reusable skills and 6 agents for Codex, Claude, Cursor, OpenCode, and Windsurf, built for maintainers
ZenML
zenml-io/mcp-zenml
MCP server to connect an MCP client (Cursor, Claude Desktop etc) with your ZenML MLOps and LLMOps pipelines
Puppeteer Vision
djannot/puppeteer-vision-mcp
McpDocServer
ruan11223344/mcpdocserver
一个基于MCP协议的开发文档服务器,专为各类开发框架文档设计
Rosetta
tikoci/rosetta
MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik
Storybook
mcpland/storybook-mcp
A MCP server for Storybook.
Tempo
ivelin-web/tempo-mcp-server
MCP server for managing Tempo worklogs in Jira
Cloudflare Remix Vite
kentcdodds/cloudflare-remix-vite-mcp
OpenStack Operations
call518/mcp-openstack-ops
90+ production-safe OpenStack tools for AI agents via MCP. Project-scoped & read-only by default. Works with Claude, Open WebUI & any MCP client. FastMCP + OpenStack SDK. Available on PyPI, Docker Hub & Smithery.
Agentic Client
peakmojo/agentic-mcp-client
A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.
npm-deprecated-check
KID-joker/npm-deprecated-check
🐦 Check for deprecated packages
JW
advenimus/jw-mcp
MCP Tools for Jehovah's Witnesses
Other risk hubs
By job
Questions
What does read-only mean here?
Is a read-only server always safe?
Why are some servers on no risk list?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does read-only mean here?
- Is a read-only server always safe?
- Why are some servers on no risk list?