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.
Akshare One MCP
3.3/10MCP server that provides access to Chinese stock market data using akshare-one
Decixa MCP
3.3/10Decixa MCP Server — intent-driven API discovery and selection for AI agents.
Raumnebenan MCP
3.3/10raumnebenan-mcp MCP server (remote, JSON-RPC 2.0)
Greenhouse MCP
3.3/10Production-ready MCP server for Greenhouse with 175 tools for recruiting teams
Agentline MCP
3.3/10Phone numbers, SMS, 2FA capture, voice calls, and email for AI agents.
Simple MCP Http
3.3/10A Test MCP server that provides tools, promts and resources
Motion MCP Public
3.3/10Remote MCP server bridging Motion to Claude
Caddy MCP
3.3/10MCP server for managing Caddy web servers via the admin API
Lemonsqueezy MCP
3.3/10LemonSqueezy MCP server for managing your store from AI assistants
MCP Compliance
3.3/10CLI tool and MCP server that tests MCP servers for spec compliance
Ssh MCP
3.3/10MCP server for SSH operations with built-in diagnostics
Tailscale MCP
3.3/10Tailscale MCP server for managing your tailnet from AI assistants
Nexus Financial
3.3/10Crypto signals, Kalshi prediction markets, wallet AML. x402 USDC on Base.
MCP Server
3.3/10Yaw MCP - one install, every MCP server, managed from yaw.sh/mcp
MCP Server
3.3/10RunSec MCP server for workspace security scanning and remediation workflows.
Mgc Blackbox
3.3/10A trusted local encrypted execution boundary for AI agents.
Ga4
3.3/10AI agent vision for Google Analytics 4 — with ROI measurement. perceptdot.com
Github
3.3/10AI agent vision for GitHub repository monitoring — with ROI measurement.
Vercel
3.3/10AI agent vision for Vercel deployments — with ROI measurement. perceptdot.com
Intent Runtime
3.3/10Express intent, get results. One unified entry point.
MCP Utils
3.3/10Data processing tools: CSV, cleaning, stats, image, report, save, shell
Whiteboard
3.1/10Whiteboard MCP server
Blockscholes MCP Server
3.1/10NaN - DO not use, test.
Workmagic MCP
3.1/10WorkMagic MCP
Zoo MCP
3.1/10A sample zoo MCP server
Jinguyuan MCP
3.1/10金谷园饺子馆的自动化管理系统
Patient MCP
3.1/101k patient MCP server
Iceberg MCP Server
2.9/10MCP Server for Apache Iceberg
Crypto Bytes
2.9/10Crypto Bytes MCP Server
Limeflight MCP
2.9/10DEPRECATED – do not use
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.