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.
Cybersecurity Intelligence
3.7/10Paid Cybersecurity Intelligence API via x402. Unpaid tool calls return 402.
Data Quality
3.7/10Paid Data Quality Intelligence API via x402. Unpaid tool calls return 402.
Defi Intelligence
3.7/10Paid DeFi Intelligence API via x402. Unpaid tool calls return 402.
Document Formats
3.7/10Paid Document Formats & Identifiers API via x402. Unpaid tool calls return 402.
Domain Security
3.7/10Paid Domain Security API via x402. Unpaid tool calls return 402.
Ecommerce Fraud
3.7/10Paid E-commerce Fraud & Order Risk API via x402. Unpaid tool calls return 402.
Ecommerce Profitability
3.7/10Paid Ecommerce Seller Profitability API via x402. Unpaid tool calls return 402.
Email Domain
3.7/10Paid Email & Domain Intelligence API via x402. Unpaid tool calls return 402.
Email Security
3.7/10Paid Email & Communication Security API via x402. Unpaid tool calls return 402.
Energy Intelligence
3.7/10Paid Energy Intelligence API via x402. Unpaid tool calls return 402.
Equity Analytics
3.7/10Paid Equity Analytics API via x402. Unpaid tool calls return 402.
Exclusion
3.7/10Paid OFAC & UK Sanctions Screening API via x402. Unpaid tool calls return 402.
Fleet Operations
3.7/10Paid Fleet Fuel Card Controls API via x402. Unpaid tool calls return 402.
Food Safety
3.7/10Paid Food Hygiene Ratings API via x402. Unpaid tool calls return 402.
Fraud Signals
3.7/10Paid Fraud & Transaction Security API via x402. Unpaid tool calls return 402.
Freight Customs
3.7/10Paid Freight & Customs API via x402. Unpaid tool calls return 402.
Fx
3.7/10Paid Exchange Rates API via x402. Unpaid tool calls return 402.
Geo Environment
3.7/10Paid Geo & Environment Lookups API via x402. Unpaid tool calls return 402.
Global Employment
3.7/10Paid Global Employment Rules API via x402. Unpaid tool calls return 402.
Grant Compliance
3.7/10Paid Grant Compliance API via x402. Unpaid tool calls return 402.
Graphql Security
3.7/10Paid GraphQL Federation Security API via x402. Unpaid tool calls return 402.
Hr Operations
3.7/10Paid HR Operations API via x402. Unpaid tool calls return 402.
Identifiers
3.7/10Paid Identifiers & Validators API via x402. Unpaid tool calls return 402.
Identity Security
3.7/10Paid Identity & Access Security API via x402. Unpaid tool calls return 402.
Indirect Tax
3.7/10Paid Indirect Tax Calculations API via x402. Unpaid tool calls return 402.
Integration
3.7/10Paid API Integration Intelligence API via x402. Unpaid tool calls return 402.
Inventory Intelligence
3.7/10Paid Inventory Intelligence API via x402. Unpaid tool calls return 402.
Kyc Identifiers
3.7/10Paid KYC National Identifier Checks API via x402. Unpaid tool calls return 402.
Legislative Intelligence
3.7/10Paid Bills & eCFR Section Lookup API via x402. Unpaid tool calls return 402.
License
3.7/10Paid License Renew API via x402. Unpaid tool calls return 402.
Llms Txt
3.7/10Paid llms.txt Intelligence API via x402. Unpaid tool calls return 402.
Local Lead Operations
3.7/10Paid Local Business Lead Operations API via x402. Unpaid tool calls return 402.
Manufacturing Quality
3.7/10Paid Manufacturing Quality API via x402. Unpaid tool calls return 402.
Marketplace Health
3.7/10Paid Marketplace Account Health API via x402. Unpaid tool calls return 402.
Options Analytics
3.7/10Paid Options Analytics API via x402. Unpaid tool calls return 402.
Physical Security
3.7/10Paid Physical & IoT Security API via x402. Unpaid tool calls return 402.
Portfolio Analytics
3.7/10Paid Portfolio Analytics API via x402. Unpaid tool calls return 402.
Prevailing Wage
3.7/10Paid Prevailing Wage API via x402. Unpaid tool calls return 402.
Privacy Operations
3.7/10Paid Privacy Operations API via x402. Unpaid tool calls return 402.
Procurement Intelligence
3.7/10Paid Procurement Intelligence API via x402. Unpaid tool calls return 402.
Product Safety
3.7/10Paid Product Safety & Recalls API via x402. Unpaid tool calls return 402.
Property Intelligence
3.7/10Paid Property Intelligence API via x402. Unpaid tool calls return 402.
Property Maintenance
3.7/10Paid Property Maintenance API via x402. Unpaid tool calls return 402.
Public Infrastructure
3.7/10Paid Public Infrastructure Lookups API via x402. Unpaid tool calls return 402.
Recruitment Operations
3.7/10Paid Recruitment Operations API via x402. Unpaid tool calls return 402.
Regulatory Intelligence
3.7/10Paid Regulatory Intelligence API via x402. Unpaid tool calls return 402.
Rental Operations
3.7/10Paid Rental Operations API via x402. Unpaid tool calls return 402.
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.