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.
Villapps
3.9/10Desktop app with a local MCP server: your coding AI builds business screens, reports and charts.
Amazon Seller MCP
3.9/10Amazon Seller Central and Ads in Claude or ChatGPT. Connect at agentxray.ai/connect.
MCP Server
3.9/10Agent-only collaboration space: pass the door, then use rooms, DMs and verifiable chains.
Snapy
3.9/10Publish text or HTML to Snapy.host and get a shareable link that shows who opened it.
Allyotter Lite
3.9/10Get a digital product ready for affiliate networks: requirements, sales-page audit, checklists.
MCP Server
3.9/10MCP server for the Aptora API: create assessments, invite candidates, pull grading results
Dwelldelta
3.9/10Is an Australian rent fair? ABS rents index check, plus sourced property and lending indicators.
Beck
3.9/10Project management for coding agents: record the approved plan, work the tasks, ask, hand off.
Arena
3.9/10Paper trade prediction markets at live prices from your AI agent, and score every trade.
MCP Server
3.9/10Check how well AI agents can read a web page: a score, the evidence and a ranked fix list.
Subtitle
3.9/10Preview: video subtitle OCR, transcription, translation, QC and export. Early access only.
MCP Server
3.9/10Proxy traffic by the GB on shared mobile 4G/5G and residential pools, paid in crypto.
Scanbase
3.9/10Website compliance checks for Russian personal data law 152-FZ: score, violations, fix instructions.
Ailimu
3.9/10Self-hosted MCP server for FileMaker. Turns chosen tables and scripts into tools for AI agents.
MCP Server
3.9/10Let your AI agent pay x402 APIs within daily caps, allowed hosts and human approval.
MCP Server
3.9/10Render App Store and Google Play screenshots from app captures: device frames, sizes, languages.
Softspoken
3.9/10A local server that lets AI assistants read your Softspoken meetings and tick off action items.
Google Ads
3.7/10Google Ads MCP server — manage campaigns, keywords, and metrics.
Salesforce MCP
3.7/10Comprehensive Salesforce administration and management
Filtrix Ai
3.7/10Filtrix MCP for image/video generation. Portal: https://agent.filtrix.ai/
MCP Server
3.7/10Our free Marketgenius investment tools as live, interactive React MCP Apps.
Recordo
3.7/10Brain dump, routines, task planning, focus, and instant thought retrieval
Tanjiren MCP
3.7/10Hosted MCP server for task-first delegation to remote workstations and workers.
MCP Server
3.7/10Analyze your campaigns any way you want, with AI.
Dotprompts
3.7/10.prompts, the home to all your AI prompts, everywhere you need them.
Jinko
3.7/10Turn your ChatGPT to a super travel agent
Cdc Mmwr
3.7/10Morbidity and Mortality Weekly Reports and disease surveillance
Cdc Svi
3.7/10SVI scores and theme breakdowns by county and tract
College Scorecard
3.7/10Higher education data: tuition, graduation rates, and earnings
Drought
3.7/10Current drought conditions and severity across the United States
Earthquake
3.7/10Real-time earthquake events from the US Geological Survey
Eia
3.7/10Energy data from EIA: electricity, fuel prices, and renewables
Epa
3.7/10Toxics Release Inventory, Superfund sites, air quality data, and AQI
Fcc Broadband
3.7/10Broadband availability, providers, speeds, and BEAD classification from the FCC
Fdic Bankfind
3.7/10Bank financials, branch locations, deposit data, and failure history from FDIC
Fema
3.7/10Federal disaster declarations, emergencies, and assistance data
Hmda
3.7/10Home mortgage lending patterns, denial rates, and fair lending data
Hrsa
3.7/10Health professional shortage areas and community health centers
Hud Housing
3.7/10Fair Market Rents, income limits, public housing, vouchers, and homeless counts
Nhtsa
3.7/10Vehicle safety recalls, complaints, and crash data from NHTSA
Noaa Climate
3.7/10Historical climate data, temperatures, precipitation, and normals
Nws Alerts
3.7/10Active weather alerts and warnings from the National Weather Service
Onet
3.7/10Job descriptions, skills, education requirements, and wage data
Samhsa
3.7/10Behavioral health statistics from SAMHSA surveys including NSDUH
Treatment Locator
3.7/10Find substance abuse and mental health treatment facilities
Usda Food
3.7/10SNAP participation, food insecurity indicators, and agricultural statistics
Va Healthcare
3.7/10VA facility locations, services, wait times, and satisfaction scores
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.