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/50
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
1,177–1,200 of 1,620 · ranked by trust score, then stars
SSH Manager
bvisible/mcp-ssh-manager
MCP SSH Server: 37 tools for remote SSH management | Claude Code & OpenAI Codex | DevOps automation, backups, database operations, health monitoring
Docfork
docfork/docfork
Docfork - Up-to-date docs for AI Coding Agents.
Docfork
docfork/docfork-mcp
Docfork - Up-to-date docs for AI Coding Agents.
Mingyu
brhiza/mingyu
八字、紫微、星盘、六爻、梅花、奇门、大六壬、小六壬、塔罗、雷诺曼、灵签、择日一站式玄学算命占卜工具包,输出结构化提示词与数据。提供公开 API、MCP Server 与 skill。
evmole
cdump/evmole
EVMole is an open-source library that analyzes deployed EVM bytecode to infer function selectors, argument types, state mutability, persistent and transient storage layout, control flow, and compiler metadata, including for unverified contracts
Calculator
78/mcp-calculator
Xiaozhi MCP sample program
Mondaycom API
mondaycom/mcp
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
Mcpadapt
grll/mcpadapt
Unlock 650+ MCP servers tools in your favorite agentic framework.
chrome-devtools-axi
kunchenguid/chrome-devtools-axi
The most agent-ergonomic browser automation
LogSeq
ergut/mcp-logseq-server
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
LogSeq
ergut/mcp-logseq
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
Daiso
hmmhmmhm/daiso-mcp
다이소를 MCP로! 뿐만 아니라 한국 로컬 리테일과 영화관 조회를 MCP, CLI, Codex Skill로 가능하게 해줍니다.
Svelte Agent Core
sveltejs/mcp
The official svelte MCP for all your agentic needs.
add-mcp
neon-solutions/add-mcp
The open MCP config tool - npx add-mcp
Llm Context
cyberchitta/llm-context.py
Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.
Roblox Studio MCP
chrrxs/robloxstudio-mcp
MCP server for Roblox Studio runtime debugging, playtest control, screenshots/input, multiplayer testing, and per-peer server/client eval from AI agents.
UniFi
enuno/unifi-mcp-server
An MCP server that leverages official UniFi API
G-Search
jae-jae/g-search-mcp
A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.
Api200
api-200/api200
API 200 is an open source API gateway to simplify 3rd-party integrations. Import endpoints, set up caching, retries, and mocks. Access all services via one URL. Monitor logs, track errors, and get alerts on API incidents.
Ant Design Components
zhixiaoqiang/antd-components-mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
Penpot
montevive/penpot-mcp
Penpot MCP server
Git
cyanheads/git-mcp-server
Clone, commit, diff, branch, merge, rebase, cherry-pick, stash, tag, and manage worktrees in local git repos via MCP. STDIO or Streamable HTTP.
Mermaid Diagram Generator
peng-shawn/mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images
WebRtcPerf
vpalmisano/webrtcperf
WebRTC performance and quality evaluation tool.
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?