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/32

Verdicts · 1,620 servers

✓SAFE913!CAUTION261✕BLOCK446

Transports

A server can list more than one transport.

1,620 servers

745–768 of 1,620 · ranked by trust score, then stars

Cypress Page Object & Test Generator

jprealini/cypress-mcp

✓SAFE B
★ 221 readstdio

Nearby Search

kukapay/nearby-search-mcp

✓SAFE B

An MCP server for nearby place searches with IP-based location detection.

★ 221 read

Server Proxy

leizongmin/mcp-server-proxy

✓SAFE B

Converts MCP protocol's SSE transport layer to a standard HTTP request/response.

★ 221 read

Trace Search

songpengfei1111-dot/tracesearch_mcp

✓SAFE B
★ 224 readstdio

cred-1

aloth/cred-1

✓SAFE B

CRED-1: Open, reproducible domain credibility dataset for automated pre-bunking of online misinformation. TypeScript library, CLI & MCP server. Check any news source's reliability from terminal, code, or AI agents. CC BY 4.0, DOI-citable.

★ 175 readstdio

@putervision/agent-reasoning-mcp

putervision/agent-reasoning-mcp

✓SAFE B

🧭 Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.

★ 159 readstdio

Taiga Ui Mcp

taiga-family/taiga-ui-mcp

✓SAFE B

Taiga UI MCP server providing documentation search and scaffolding tools.

★ 154 readstdio

call-a-human-mcp

nishantmodak/call-a-human-mcp

✓SAFE B

MCP server that gives any AI phone a friend options : ask a human or request approval via Slack or macOS dialogs before taking irreversible actions.

★ 152 readsse

mcp-server-polarion

devemberx/mcp-server-polarion

✓SAFE B

MCP server for Polarion ALM — read and write documents, work items, test runs, traceability links, and comments from any MCP-compatible AI assistant

★ 152 readstdio

medical-terminologies-mcp

SidneyBissoli/medical-terminologies-mcp

✓SAFE B

Unified MCP server for six medical terminologies (ICD-11, LOINC, RxNorm, MeSH, ATC, CID-10) with authoritative WHO ICD-10→ICD-11 mapping and provenance on every response. Hosted endpoint: no install, no credentials.

★ 1533 readstdio

pubcrawl

nickjlamb/pubcrawl

✓SAFE B

MCP server giving AI assistants verifiable access to PubMed, Europe PMC, US/UK drug labelling, and ClinicalTrials.gov. Built by PharmaTools.AI.

★ 1515 readstdio

storybook-mcp-server

stefanoamorelli/storybook-mcp-server

✓SAFE B

MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots. Built with TypeScript and Model Context Protocol SDK.

★ 146 readstdio

whoop-mcp-server

yuridivonis/whoop-mcp-server

!CAUTION B

Your WHOOP recovery, sleep, strain and workouts in Claude, ChatGPT or other MCP apps. Self-hosted.

★ 145 readstdio

openhammer-api

EshanPrakash/openhammer-api

✓SAFE B

Comprehensive Warhammer 40K API with 2,748 units across 35 factions and 2 game editions (10th and 11th). Built with FastAPI, featuring 29 endpoints. Also available as a live MCP server.

★ 139 readstreamable-http

ibge-br-mcp

SidneyBissoli/ibge-br-mcp

✓SAFE B

MCP Server for IBGE APIs - Brazilian geographic, demographic and statistical data

★ 1221 readstdio

xiangsu-mcp

sleepyquq/xiangsu-mcp

✓SAFE B

像塑 MCP | AI Agent scene editing, scripting and playtesting for Douyin Xiangsu. Effect House compatibility unverified.

★ 121 readstdio

oauth-callback

kriasoft/oauth-callback

✓SAFE B

OAuth 2.0 login for CLI tools and desktop apps: opens the browser and captures the authorization code on a loopback redirect (RFC 8252). Node.js, Deno, Bun. One-line MCP client auth.

★ 111 readstreamable-http

uiflowchartcreator

umshere/uiflowchartcreator

✓SAFE B

MCP server for creating UI flowcharts

★ 111 readstdio

mcp-listen

decibri/mcp-listen

✓SAFE B

Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.

★ 103 readstdio

OpenFinData

robertoecf/OpenFinData

✓SAFE B

Dados Financeiros Abertos — infraestrutura open source para dados financeiros públicos do Brasil via API REST, MCP, CLI e Python.

★ 1010 read

bcb-br-mcp

SidneyBissoli/bcb-br-mcp

✓SAFE B

MCP server for Brazil Central Bank (BCB) data — Selic, IPCA, exchange rates, GDP for AI agents

★ 98 readstdio

genpark-hub

alphaparkinc/genpark-hub

✓SAFE B

GenPark & OpenClaw Premium Growth Hub, Showcase and Live Skill Generator.

★ 913 read

solana-sniper-mcp

nirholas/solana-sniper-mcp

✓SAFE B

Lightweight, embeddable pump.fun sniper engine for 3D AI agents — multi-agent, multi-user, with pluggable wallet/store/RPC adapters. Library + CLI + MCP server + x402 paid API.

★ 97 readstdio

Doppler MCP Server

DopplerHQ/mcp-server

✓SAFE B
★ 82 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.