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/46
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
1,081–1,104 of 1,620 · ranked by trust score, then stars
Yingdao RPA
ying-dao/yingdao_mcp_server
影刀RPA MCP Server
Custom
sharan-kumar-r/custom-mcp-server
MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
Codesearch
flupkede/codesearch
Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.
Figma
jayzeedesign/figma-mcp
NestJS Starter
hmake98/nestjs-starter
Production-ready NestJS boilerplate — JWT auth, Prisma, Redis, BullMQ, Swagger, i18n, and full AI developer workflows (Claude Code + GitHub Copilot) with spec-driven feature scaffolding.
Yby6 Video Parser
yangbuyiya/yby6-crawling-short-video-mcp
本项目是一个基于 FastMCP 的全网短视频去水印解析服务,支持多平台视频分享链接的解析,自动提取视频真实地址及相关信息。 适用于需要批量解析、去水印、采集短视频的场景。本项目还支持视频内容文本提取功能,可以通过语音识别将视频内容转为文本。
TeamCity
daghis/teamcity-mcp
Model Context Protocol (MCP) server for JetBrains TeamCity: control builds, tests, agents and configs from AI coding assistants.
codegraph-brain
zaebee/codegraph-brain
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local, deterministic, SQLite.
corpus.333.eco
333eco/corpus.333.eco
An MCP server for an open-licensed corpus, served with verifiable provenance — sha256, DOI and OpenTimestamps with every response.
@mcp-z/oauth
mcp-z/oauth
Multi-account orchestration and secure token storage for OAuth-based MCP servers
Sse Pattern
sidharthrajaram/mcp-sse
A working pattern for SSE-based MCP clients and servers
Architectural Snapshot
dejo1307/archmcp
Understand, analyze, and govern software systems across repositories, languages, and technologies.
Enola
dejo1307/enola
Understand, analyze, and govern software systems across repositories, languages, and technologies.
Enola
enola-labs/enola
Understand, analyze, and govern software systems across repositories, languages, and technologies.
apple-mail-mcp
sweetrb/apple-mail-mcp
MCP server for Apple Mail - read, search, send, and manage emails via Claude and other AI assistants
Kanban
bradrisse/kanban-mcp
MCP Kanban is a specialized middleware designed to facilitate interaction between Large Language Models (LLMs) and Planka, a Kanban board application. It serves as an intermediary layer that provides LLMs with a simplified and enhanced API to interact with Planka's task management system.
Fast ThreatIntel
4r9un/fastmcp-threatintel
AI-Powered Threat Intelligence MCP tool
VibeCoding
hyunjunjeon/vibecoding-lg-mcp-a2a
ttimes 바이브코딩 컨퍼런스 라이브 코딩 - 리서치 / 보고서 작성 Multi Agent 프로젝트
Numera-Image-Gen-MCP
KiaroSama/Numera-Image-Gen-MCP
Local TypeScript MCP server for provider-independent image generation and editing, with OmniRoute, 9router, native image APIs, and ComfyUI adapters.
knowledge-mcp
SterlingJF/knowledge-mcp
Plain, structured thinking while you work. It's free, open, and local-first.
agent-cold-email
YS-projectcalc/agent-cold-email
Coldrig — cold email infrastructure run entirely by your coding agent (Claude Code / Codex / Cursor / Cline). One token, 28 intent-level MCP + HTTP tools and an npm CLI: domain purchase, mailboxes, warmup, sequences, replies, deliverability guardrails. Free fault-injecting sandbox.
Kindly Web Search
shelpuk-ai-technology-consulting/kindly-web-search-mcp-server
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.
Confluent
confluentinc/mcp-confluent
Tool Kit
getfounded/mcp-tool-kit
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
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?