The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Rtl MCP
3.9/10Give coding agents right-to-left awareness: lint, normalise Arabic, detect direction.
Verify
3.9/10Independent x402 observatory on Base. Sealed decomposition + endpoint audits paid over x402 itself.
Security
3.9/10Scan a running app or repo for leaked secrets, exposed routes and open RLS, and verify live keys
Andish MCP
3.9/10Knowledge-graph memory for your team's documents. Answers cite the source, not a summary.
Flydocs
3.9/10Spec-driven development workflow: your agent works issues, sessions and the status lifecycle.
Agent
3.9/10Search prediction markets, preview trades, and place explicitly confirmed Pariflow orders.
Zillow
3.9/10Zillow property data for AI agents, 50+ fields per US property. Not affiliated with Zillow Group.
Tiled MCP
3.9/10Inspect, validate and surgically edit Tiled map files (.tmx/.tmj) — byte-preserving, 12 tools.
Jsonshim
3.9/10Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Diagnostics
3.9/10Grade an MCP server's auth against the spec and diagnose which layer a failure is in.
Grantor MCP
3.9/10Wrap any MCP server with enforced, bounded, revocable permissions — grant, narrow, check, revoke.
Warden
3.9/10Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.
MCP Server
3.9/10Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.
MCP Server
3.9/10Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.
Kainext Binance MCP
3.9/10Security-first Binance Spot MCP + honest crypto analyst. 25 tools, 5 prompts, human-gated orders.
Oracle
3.9/10Keyless multichain crypto desk: chain reads + prepare-only unsigned txs. Your wallet signs.
Cluster Validator
3.9/10Read-only health validation for Windows Server failover clusters running SQL Server FCI.
MCP Server
3.9/10Run website audits and track site health scores, findings, and regressions from any MCP client.
MCP Server
3.9/10Design canvas for coding agents: real editable vectors, auto layout, components, export to code.
Synmerco
3.9/10Escrow, trust scores, and marketplace for AI agent commerce on 5 chains. 41 tools, 8 free.
Didwork
3.9/10Verify that an agent's claimed outcome actually happened, using independently gathered evidence
Reviewgate
3.9/10Code review against your team standards, before the pull request: generator finds, judge confirms
MCP Server
3.9/10Generate PDF, DOCX, and XLSX documents from JSON data and create reusable templates via Docmill
MCP Server
3.9/10Non-custodial trading infrastructure for AI agents across prediction markets, crypto, and options.
Geoedge MCP
3.9/10Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access
Mails Agent Email
3.9/10A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
MCP Server
3.9/10Sandbox-only MuPag MCP server for approved payments, subscriptions, refunds, and reconciliation.
Vocaless
3.9/10Remove vocals from local audio files and transpose instrumentals through Vocaless.
Sakupa
3.9/10Publish and manage company websites from your AI chat. Free 30-day sites; no Sakupa account.
Weakspot
3.9/10Audit Solidity and Rust smart contracts from your editor. Pays per audit in USDC over x402.
Unstringify
3.9/10Fix broken JSON by line, validate, convert, read CSV/NDJSON/logs as records, unpack, compare. Local.
Indiebob
3.9/10IndieBob for agents: metrics, posts, cold outreach written per prospect, and what to do next.
Control MCP Server
3.9/10Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots.
Commerce Gate
3.9/10Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.
Gdmaestro
3.9/10Drive the Godot engine from an AI coding agent: build, run, play, and verify your game live.
Firekey MCP
3.9/10Manage FireKey browser profiles and browser lifecycles through an authenticated localhost API.
Cad Control MCP Server
3.9/10Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots.
Ronin Buyer
3.9/10Web research and source retrieval. Native MCP tool with x402 Base USDC payment, 0.010000 per call.
Tada
3.9/10Your coding agent asks Tada to work through a feature in a real browser and gets back a verdict.
Benchboss
3.9/10Play Chess, RPS-N and Safehouse Protocol via MCP. Public replays; GitHub verification required.
Quickpeek
3.9/10Turn a URL into a narrated demo video: real browser walkthrough, AI voiceover, captions burned in.
Audio Llm
3.9/10Audio, captions, PDF extraction, image OCR and LLM APIs with capped USDC payments.
Alchemite MCP
3.9/10Design experiments and make predictions for materials & chemicals properties in your local agent
React Native MCP
3.9/10MCP server for agent-driven React Native and Expo development and mobile testing
Cli
3.9/10Deploy any Git branch to a live HTTPS preview URL from your agent. No Dockerfile required.
Magic Hdl
3.9/10Analyze and verify Verilog, SystemVerilog, and VHDL projects from AI agents over MCP.
Clack
3.9/10Capture, read, mark up and edit screenshots and recordings in Clack for Mac. Needs the Clack app.
Store
3.9/10Browse the Binary & Thread catalogue, stage a cart, get a checkout link. No card data in chat.
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.