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.
Kyras
4.1/10Marketing analytics from your real data: GA4, Piano, Matomo, Shopify, Google Ads, Meta Ads.
Naturali
4.1/10Configure AI agents, give them knowledge and tools, and read back every generation they run.
Organicus
4.1/10Your brand's visibility in AI assistants: audit findings, weekly answers, and work to approve.
Pozeidon
4.1/10Analyse ads and manage creatives across Meta, Google Ads, AppLovin, Unity, Mintegral and TikTok.
Company Context
4.1/10Answers about your own company from its recorded knowledge, and shows where its sources disagree.
MCP Server
4.1/10Work a decision through SwingFactor’s method: build and challenge a model of what could change it.
MCP Server
4.1/10A design agent in your coding agent's loop: briefs each screen, reviews UX and visual quality.
Tigertiger
4.1/10Chief of Staff, strategy and writing tools that give your Claude subscription structure and memory.
Wayb
4.1/10A catalogue of indie products, not a registry of MCP servers. Reading needs no credential.
Awardia
4.1/10EU public tenders for AI agents: open tenders, award history, competitors and bid intelligence.
MCP Server
4.1/10Place real phone calls, read transcripts, run a live interpreter and buy numbers.
Research
4.1/10Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools.
Instagram comment-to-DM automation your AI can set up and leave running, on the official Meta API.
Koboshi
4.1/10Save vocabulary from any AI chat; see each word in every language you know; review it with FSRS.
Lexpad
4.1/10Your vocabulary notebook: save, browse, edit and practise your own words with spaced repetition.
Ai Text
4.1/10Paste a draft and see the habits that make writing read like it came from an AI model.
Api
4.1/10YouTube transcripts, open jobs from careers pages, app store reviews and X posts for AI agents.
Business Days
4.1/10Count working days between two dates, add business days to a date, or list public holidays.
Buyersignals
4.1/10Companies with a recent, dated, public sign they may buy, from SEC filings and job boards.
Cars
4.1/10Check a US car: decode a VIN, see recalls, crash ratings, owner complaints and fuel economy.
Catalog Qa
4.1/10Check an online store's product catalog before you import it or send it to a shopping feed.
Citations
4.1/10Paste a bibliography or a single reference and find out whether the papers are real.
Company Jobs
4.1/10Open jobs at the companies you name, read straight from their public careers boards.
Countrystats
4.1/10Official economic and demographic figures for a country, with IMF projections and World Bank data.
Cve
4.1/10Triage a CVE: how severe it is, whether it is exploited, and how likely exploitation is.
Dev Facts
4.1/10Software end-of-life dates, open-source licenses, browser support for web features and RFC facts.
Docs
4.1/10Count the words in a text, make a calendar .ics file, or turn a table into a CSV file.
Food
4.1/10Look up a packaged food by barcode, search and compare products, and check listed allergens.
Hire
4.1/10Split a job into work AI can do now, work AI drafts for a person to approve, and work for a person.
Industry Pulse
4.1/10What happened in AI coding agents like Claude Code, Codex, Cursor and Copilot, and what people say.
Live Card
4.1/10Turn a cover and a short animation, supplied as HTML, into an Apple Live Photo, an MP4 and a GIF.
Lpcheck
4.1/10Read a liquidity pool's volume, TVL and fee APR over 1 and 7 days, and spot a short APR spike.
Mailcheck
4.1/10Check how a domain is set up for email and who it is registered with, from public DNS data.
Market Indicators
4.1/10Calculate SMA, EMA, RSI, MACD, Bollinger Bands, ATR, stochastic and VWAP over a price series.
Names
4.1/10Check whether the domain for a startup, product or business name is already registered.
Outreach Desk
4.1/10Score inbound recruiter and sales pitches on relevance, specificity, cadence and spam signals.
Packages
4.1/10Check an npm or Python package, or a package.json, for vulnerabilities and upkeep.
Papers
4.1/10Find research papers and arXiv preprints, and get an abstract and free full text from a DOI or id.
Postkit
4.1/10Turn a topic into posts that fit each platform, short video scripts, and an animated launch clip.
Recalls
4.1/10Check US recalls for a car, a baby product, a food or a medicine in the official recall databases.
Send Out
4.1/10Turn assistant output into ready-to-send action links and files, with no sign-in.
Site Check
4.1/10Look at what your website or online store tells crawlers, link previews and AI agents.
Store Prices
4.1/10Ask what an online store sells, what it charges and what changed since the last time anyone looked.
Tariffs
4.1/10Find candidate customs tariff codes for a product and read the import duty on a code.
Taste
4.1/10Turn the reference images you collect into a written design taste your assistant can follow.
Tax
4.1/10Get the US federal tax numbers right, with the IRS document each one comes from.
Trade Chart
4.1/10A candlestick chart for a public ticker, with volume, the indicators you name and a plain read.
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.