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/18

Verdicts · 1,620 servers

✓SAFE913!CAUTION261✕BLOCK446

Transports

A server can list more than one transport.

1,620 servers

409–432 of 1,620 · ranked by trust score, then stars

Aws Bedrock Integration

davidshtian/mcp-on-aws-bedrock

✓SAFE B

A simple and clear example for implementation and understanding Anthropic MCP (on AWS Bedrock).

★ 551 readstreamable-http

Azure AI Agents

farzad528/mcp-server-azure-ai-agents

✓SAFE B

Model Context Protocol Servers for Azure AI Search

★ 555 read

OpenAlex Research

oksure/openalex-research-mcp

✓SAFE B

MCP server for the OpenAlex API — search 240M+ scholarly works, analyze citations, track research trends, and map collaboration networks

★ 5526 readstdio

SearXNG Scraper

pwilkin/mcp-searxng-public

✓SAFE B

An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result

★ 551 read

Thoughtful Claude

martinbowling/thoughtful-claude

✓SAFE B

MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔

★ 551 read

WolframAlpha LLM

garoth/wolframalpha-llm-mcp

✓SAFE B

An MCP Server for WolframAlpha's LLM API, able to return structured knowledge & solve math

★ 553 readstdio

PlantUML

infobip/plantuml-mcp-server

✓SAFE B
★ 544 readstdio

Claude Code Delegator

fjgbue/claude-delegator-deepseek-mcp

✓SAFE B

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.

★ 533 read

Claude Delegator

12122j/claude-delegator-deepseek-mcp

✓SAFE B

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.

★ 533 read

ROADrecon

atomicchonk/roadrecon_mcp_server

✓SAFE B

Claude MCP server to perform analysis on ROADrecon data

★ 539 read

Apple Notes

henilcalagiya/mcp-apple-notes

✓SAFE B

An local mcp server for interacting with Apple Notes via LLM.

★ 524 readstdio

Crypto Fear Greed Index

kukapay/crypto-feargreed-mcp

✓SAFE B

Providing real-time and historical Crypto Fear & Greed Index data

★ 523 read

DeepSRT

deepsrt/deepsrt-mcp

✓SAFE B
★ 522 readstdio

GotoHuman

gotohuman/gotohuman-mcp-server

✓SAFE B
★ 523 readstdio

OneKey Gateway

aiagenta2z/onekey-gateway

✓SAFE B

OneKey Agent Gateway access to Commercial APIs, Skills, MCPs Build once and Ship 10× faster. For devs & builders, A unified API registry to serve and distribute across all agent formats—CLI, REST, MCP, and Skills—eliminating multiple builds. Access 30+ categories like search, image, finance, and 3D

★ 521 readstdio

VChart

visactor/vchart-mcp-server

✓SAFE B

A Model Context Protocol (MCP) server for the @visactor/vchart that enables AI assistants to generate interactive charts and visualizations.

★ 5216 readsse

YouTube Intelligence

janghyuckyun/mcp-youtube-intelligence

✓SAFE B

MCP server for YouTube transcript extraction, channel monitoring, and content intelligence

★ 5210 readstdio

Credit Optimizer V5

rafsilva85/credit-optimizer-v5

✓SAFE B

Save 47% on Manus AI credits automatically. Zero downsides. Pays for itself in ~27 prompts. Free MCP Server (PyPI) + $12 Manus Skill bundle with Fast Navigation (115x speed boost).

★ 513 readstdio

DNStwist

burtthecoder/mcp-dnstwist

✓SAFE B

MCP server for dnstwist, a powerful DNS fuzzing tool that helps detect typosquatting, phishing, and corporate espionage.

★ 511 readstdio

EndNote

gokmengokhan/endnote-mcp

✓SAFE B

Connect your EndNote reference library to Claude AI — search, cite, and read PDFs directly in conversations

★ 5112 readstdio

FastAPI SSE

panz2018/fastapi_mcp_sse

✓SAFE B

A working example to create a FastAPI server with SSE-based MCP support

★ 512 readsse

Image Generation

gongrzhe/image-generation-mcp-server

✓SAFE B

This MCP server provides image generation capabilities using the Replicate Flux model.

★ 511 readstdio

Ledger CLI

minhyeoky/mcp-server-ledger

✓SAFE B

A Model Context Protocol server for interacting with Ledger CLI, a powerful double-entry accounting system. This server enables Large Language Models to query and analyze financial data through a standardized interface, making it easy for AI assistants to help with financial reporting, budget analys

★ 519 read

Zig

opensvm/zig-mcp-server

✓SAFE B

A Model Context Protocol (MCP) server that provides Zig language tooling, code analysis, and documentation access. This server enhances AI capabilities with Zig-specific functionality including code optimization, compute unit estimation, code generation, and best practices recommendations.

★ 517 readstdio

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.