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.
Data New Model Release Tracker Huggingface Ai
4.9/10New AI models on HuggingFace: releases, weights. Register in-session — free testnet funds.
Made MCP
4.9/10Generate and edit images and video with MADE: model catalog with transparent per-job pricing.
Data Llm Release Model Availability Tracker
4.9/10LLM releases: new models, availability, context. Register in-session — free testnet funds.
Kyma
4.9/10Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat.
Data New Dataset Release Huggingface Tracker
4.9/10New HF datasets: releases, licenses, updates. $0.01/query. Register in-session — free testnet funds.
Hubris MCP
4.9/10OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.
Data Ai App Demo Huggingface Spaces Discovery
4.9/10New Hugging Face Spaces: fresh AI app demos & UIs. Register in-session — free testnet funds.
Json To Types
4.9/10Convert JSON samples into TypeScript interfaces and Zod schemas, with inference caveats.
Getrun
4.9/10Image, video, audio and chat from 61 AI models through one connector. Pay per use, no subscription.
Performix Site
4.9/10Performix public corpus over MCP: guides, books, evidence, outcome models, plus a computing tool.
Data Openai Announcement Model Release News
4.9/10OpenAI announcements: models, releases, news. $0.01/query. Register in-session — free testnet funds.
Data Deepmind News Google Ai Model Release
4.9/10Official DeepMind blog: Gemini & AI model releases. Register in-session — free testnet funds.
Stytrix MCP
4.9/10AI fashion design MCP: generate concepts, models, fabrics & looks live on your StyTrix canvas.
Trent
4.9/10Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Data Huggingface Trending Ai Model
4.9/10HuggingFace trending models — what's hot now. $0.01/query. Register in-session — free testnet funds.
Ai Wave
4.9/10AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Outfit Assistant
4.9/10Your own closet in your AI: outfits from clothes you own, rendered on a model inline.
Merofoundry
4.9/10Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.
Fapd
4.9/10Cited daily digests of official US federal publications. Read-only; no inference.
MCP Server
4.9/10Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
Heystack
4.9/10Observability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts.
MCP Server
4.9/10Uncensored image, image-to-video and chat generation for adult apps. OpenAI-compatible, pay per use.
Agentbuilt
4.9/10Free AI-readiness audit of any URL: AI crawler rules, JS-free text, JSON-LD, llms.txt. Tool catalog.
Redaction
4.9/10Takes the people out of text before a model sees it, and puts them back in the reply.
Decider
4.9/10A decision model for the calls that don't have a right answer. The better option, with a reason.
MCP Server
4.9/10Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
Inventory Fulfillment
4.9/10Safety-stock & reorder planning, FBA-vs-FBM decision, and inventory health audit for sellers
Vibemarketolog
4.9/10Landing A/B tests, Yandex Wordstat, Metrika, Direct and 170+ AI models in ChatGPT, Claude, Cursor
Heatpulse
4.9/10AI-news gateway for agents: curated events, digests, live LLM leaderboards, intent router.
Commodities
4.9/10Kalshi gold, silver, oil and crypto: live 15-minute markets, perps liquidation, and model edges.
Leafmelt
4.9/10PDF/Word/Excel/HTML to clean Markdown for LLMs and RAG. Keys $19/mo; 50 free calls a day.
MCP Server
4.9/10500+ AI models in one account: find and price models, make images, video, speech and text.
MCP Server
4.9/10Generate images, video, audio and short films with 140+ AI models from any MCP client.
Insumer
4.9/10Wallet auth: send a wallet and conditions, get a signed boolean across 37 chains.
Quillm
4.9/10Dashboards, trackers and docs your agents build and keep current. Your team reads them by link.
Vram MCP
4.9/10Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Call Me
4.9/10Your AI rings your iPhone, speaks its question, and gets your spoken answer back as text.
Benchgecko
4.9/10AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
Ephemeris
4.9/10Probabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled.
Visiting Minds
4.9/10A public guest room for AI agents: leave one thing you learned today, read what other models left.
Ctxstore MCP
4.9/10Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
Unreal MCP Server
4.7/10A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Metehangzl Pokemcp
4.7/10Provide detailed Pokémon data and information through a standardized MCP interface. Enable LLMs an…
Scrapegraphai Scrapegraph MCP
4.7/10Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
Alex Llm Attack MCP Server
4.7/10Query and retrieve information about various adversarial tactics and techniques used in cyber atta…
Callmybot Cookbook MCP Server
4.7/10Count occurrences of any character in your text instantly. Specify the character and get precise c…
Callmybot Domoticz
4.7/10Greet anyone by name with a friendly hello. Explore the origin of 'Hello, World' for context in de…
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.