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.
Vidlens MCP
4.1/10YouTube intelligence layer for AI agents. 41 tools, 10 modules, zero config.
MCP Server
4.1/10On-chain wallet analytics and trading strategies on Base for AI assistants
Adaptive Memory Graph
4.1/10Persistent memory for Claude via weighted, interconnected knowledge nodes.
Ap MCP Server
4.1/10Model Context Protocol (MCP) server for the Associated Press Media API
Aichat
4.1/10Inter-agent communication for multi-agent Claude Code workflows.
Rclone
4.1/10MCP server for the Rclone RC API, with selectable toolsets.
Trade Router MCP
4.1/10TradeRouter.ai MCP Server — Solana swap & limit order engine.
Nerve Rpc
4.1/10MCP server for Nerve blockchain JSON-RPC & REST API for AI Agents
Crabcut
4.1/10Turn YouTube videos into short-form clips from any AI assistant
MCP Server
4.1/10Model Context Protocol server for Refgrow affiliate program management API
Appstore Screenshots
4.1/10Generate professional App Store screenshots by matching any top app's style.
Docbot MCP
4.1/10Bidirectional CSV JSON Markdown transformer
Web Task Api
4.1/10Browser tasks, sessions, and recipes for MCP and HTTP automation.
Rigour
4.1/10Quality gates for AI agents. Lint, test, build checks with memory persistence.
Rill
4.1/10AI agent wallets, Proof of Conduct reputation, and concentration decay on L1
Recite MCP
4.1/10Local MCP server for Recite receipt processing with ledger and memory tools.
Claude Army
4.1/10Orchestrate multiple Claude Code agents in parallel from chat
Ros MCP Server
4.1/10Connect AI models like Claude & ChatGPT with ROS robots using MCP
Kustodia Escrow
4.1/10Agentic escrow payments — fiat + crypto, 36 MCP tools, 10 chains, FHE privacy
A11Y
4.1/10Alt text, headings, contrast, ARIA for AI agents
Api
4.1/10HTTP client, JWT decode, header analysis for AI agents
Cache
4.1/10Cache headers, CDN, LRU simulation for AI agents
Color
4.1/10Color convert, palette, contrast checker for AI agents
Config
4.1/10JSON, YAML, TOML, INI config tools for AI agents
Crypto
4.1/10Hash, encode, UUID, password analysis for AI agents
Dep
4.1/10License check, outdated deps, security for AI agents
Docker
4.1/10Docker container management and Dockerfile analysis
Docs
4.1/10JSDoc, README, changelog generation for AI agents
Env
4.1/10Dotenv parser, ports, system info for AI agents
File
4.1/10Dir tree, file stats, duplicates, LOC for AI agents
Git
4.1/10Git log, diff, blame, branch stats for AI agents
Github
4.1/10GitHub analytics - repos, PRs, issues, releases, contributors
I18N
4.1/10Locale detect, translations, plurals for AI agents
Image
4.1/10Image metadata, favicon, OG image for AI agents
Json
4.1/10JSON/YAML/CSV validate, diff, transform for AI agents
Lint
4.1/10Style check, naming, complexity analysis for AI agents
Log
4.1/10Log parse, filter, analyze for AI agents
Markdown
4.1/10Markdown TOC, lint, format, stats for AI agents
Math
4.1/10Calculator, units, statistics for AI agents
Network
4.1/10DNS, IP info, SSL, WHOIS, ping for AI agents
Perf
4.1/10Benchmark, memory, Big O analysis for AI agents
Regex
4.1/10Regex test, explain, replace patterns for AI agents
Schema
4.1/10JSON Schema, TypeScript types, mocks for AI agents
Seo
4.1/10SEO analysis - meta tags, keywords, links, page speed
String
4.1/10String analyzer, diff, templates for AI agents
Task
4.1/10Todo, priority, estimation, burndown for AI agents
Testing
4.1/10Test generation, mocks, coverage analysis for AI agents
Time
4.1/10Timezone, dates, cron, timestamps for AI agents
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.