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.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Read-only MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/read-only/page/15

Verdicts · 1,620 servers

✓SAFE913!CAUTION261✕BLOCK446

Transports

A server can list more than one transport.

1,620 servers

337–360 of 1,620 · ranked by trust score, then stars

HexDocs

bradleygolden/hexdocs-mcp

✓SAFE B

Semantic search for Hex documentation, right in your editor ✨

★ 705 readstdio

Logseq Tools

joelhooks/logseq-mcp-tools

!CAUTION B

mcp server for logseq graph

★ 7016 readstdio

Shannon Thinking

olaservo/shannon-thinking

✓SAFE B

MCP server for applying a Claude Shannon-inspired problem-solving pattern

★ 701 readstdio

Web Search

uk0/web-search-fast

!CAUTION B

一个简单的本地 web search mcp ,可以集群规模化进行对外提供服务。

★ 701 readstdio

AI Diagram & Prototype Generator

simonutd/ai-diagram-prototype-generator-mcp-server-

!CAUTION B

AI Diagram & Prototype File Generator (MCP Server)

★ 693 readstdio

Claude Memory

whenmoon-afk/claude-memory-mcp

✓SAFE B

Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history.

★ 693 readstdio

Datadog

geli2001/datadog-mcp-server

✓SAFE B

MCP server interacts with the official Datadog API

★ 6910 readstdio

datadog-mcp-server

GeLi2001/datadog-mcp-server

✓SAFE B

MCP server interacts with the official Datadog API

★ 6910 readstdio

Deepseek Thinker

ruixingshi/deepseek-thinker-mcp

✓SAFE B

A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.

★ 691 readstdio

Design System

freema/mcp-design-system-extractor

!CAUTION B

MCP (Model Context Protocol) server that enables AI assistants to interact with Storybook design systems. Extract component HTML, analyze styles, and help with design system adoption and refactoring.

★ 698 readstdio

Google Search

adenot/mcp-google-search

✓SAFE B
★ 692 readstdio

Linked API

linked-api/linkedapi-mcp

✓SAFE B

MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data.

★ 695 readstdio

agentmail-mcp

agentmail-to/agentmail-mcp

✓SAFE B

Email inboxes for AI agents: send, receive, reply, search, and manage threaded email over MCP.

★ 684 readstdio

Deepseek R1

66julienmartin/mcp-server-deepseek_r1

✓SAFE B

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

★ 681 readstdio

Xcode Index

block/xcode-index-mcp

✓SAFE B

Give AI agents access to Xcode's index

★ 684 read

Claude Code Emacs

yuya373/claude-code-emacs

✓SAFE B

This package provides seamless integration with Claude Code, allowing you to run AI-powered coding sessions directly in your Emacs environment.

★ 6714 readstdio

Unity API

codeturion/unity-api-mcp

✓SAFE B

Instant, accurate Unity API lookups instead of expensive source file reads, saving your agent tokens, context, and hallucinations

★ 675 readstdio

AgentMail

agentmail-to/agentmail-mcp

✓SAFE B

Email inboxes for AI agents: send, receive, reply, search, and manage threaded email over MCP.

★ 663 readstdio

Astro Docs

withastro/docs-mcp

✓SAFE B

Astro Docs MCP Server

★ 661 readstreamable-http

AI Federation Network

ruvnet/federated-mcp

✓SAFE B

This implementation follows the official MCP specification, including proper message framing, transport layer implementation, and complete protocol lifecycle management. It provides a foundation for building federated MCP systems that can scale across multiple servers while maintaining security and

★ 656 readstdio

Legifrance

pylegifrance/mcp-server-legifrance

✓SAFE B

Legifrance MCP Server

★ 653 readstdio

MyChatArchive

1ch1n/mychatarchive

✓SAFE B

Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and search via MCP server. Zero cloud, zero cost.

★ 656 readsse

ReactBits

ceorkm/reactbits-mcp-server

✓SAFE B

MCP server providing access to 135+ animated React components from ReactBits.dev (9.2/10 test score)

★ 655 readstdio

Searchoor

0xdaef0f/job-searchoor

✓SAFE B

A simple MCP server that delivers you jobs based on your needs

★ 651 read

Other risk hubs

By job

Questions

What does read-only mean here?
A server is listed here when its source declares at least one tool and every tool is classed read: no write tools and no destructive tools.
Is a read-only server always safe?
No. 913 are SAFE, 261 CAUTION and 446 BLOCK on this list. A tool list says what the tools do, not whether the surrounding code is clean, so a read-only server can still be BLOCK.
Why are some servers on no risk list?
615 servers declare no tools we can read, because they build the list at runtime. They cannot be called read-only, so they appear on none of the risk hubs.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.