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/62
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
1,465–1,488 of 1,620 · ranked by trust score, then stars
Tree-sitter Analyzer
aimasteracc/tree-sitter-analyzer
Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo.
NeuronDB
neurondb/neurondb
NeuronDB PostgreSQL extension: vector similarity search (HNSW, IVFFlat), embeddings, kNN, ML in SQL, and hybrid full-text + vector retrieval.
Open Code Review
raye-deng/open-code-review
🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD Action.
GroundTruth-MCP
rm-rf-prod/GroundTruth-MCP
Self-hosted MCP server for live documentation, code audits, and best practices. 793+ curated libraries, 107 audit patterns, no rate limits.
hronaut
hronaut/hronaut
The browser your coding agent can come back to — visible, persistent, isolated workspaces over MCP.
celeste-cli
whykusanagi/celeste-cli
Agentic terminal AI assistant with a Bubble Tea TUI, code-graph review, semantic search, multi-provider LLMs, and MCP tools.
MCPGateway
yeelam-gordon/MCPGateway
Share local MCP servers across coding-agent sessions: avoid duplicate backend memory and startup work. Keep the agent-side MCP connection across settled configuration-only restarts (SDK/stdio). Tool discovery and exclusive workflows; sharing adds overhead.
CodeGraphContext
shashankss1205/codegraphcontext
An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.
Crw
us/crw
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma
CKB
simplyliz/ckb
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping
CKB
simplyliz/codemcp
Code intelligence for AI assistants - MCP server, CLI, and HTTP API with symbol navigation, impact analysis, and architecture mapping
Shinkai
dcspark/shinkai-local-ai-agents
Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.
Shinkai
dcspark/shinkai-apps
Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.
Rails AI Context
crisnahine/rails-ai-context
45 MCP tools that give AI coding agents ground truth about your Rails app: schema, models, routes, controllers, views, jobs, conventions. Works with Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI. MCP or CLI, in-Gemfile or standalone, and it still answers when the app can't boot.
React Native AI Debugger
igorzheludkov/react-native-ai-debugger
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
react-native-ai-devtools
igorzheludkov/execbro
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
european-parliament-mcp-server
Hack23/European-Parliament-MCP-Server
European Parliament MCP Server - Political intelligence for AI agents
ai-appsec
subodhkc/ai-appsec
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.
kenny
nullthrone/kenny
Self-hosted remote administration and fleet monitoring for Windows PCs in a family setting, operated through Claude (MCP) and a web dashboard.
sigelo
csigelo/sigelo
Portable, offline-verifiable identity for AI agents: Ed25519 DIDs, signed attestations any world checks without a server, a Monero keeper that holds the money so the agent never does. Draft, wire sigelo/0.
Peekaboo 🫣 — Mac automation that sees the screen and does t
openclaw/Peekaboo
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Pdf Reader Mcp
sylphlab/pdf-reader-mcp
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Anymd
SylphxAI/anymd
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
PDF Reader
sylphxltd/pdf-reader-mcp
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
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?