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.
Site
3.7/10ProbeLedger: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Proofzo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10PTOroom: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Rapportvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Rebadgo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Recallvia: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Reconzy: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10RemitDeck: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10RentRollDesk: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Reputzo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Reqnix: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Requly: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Retainvia: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Retainvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Reviewvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Rollupvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Rotazo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10RoughInDesk: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10RunbookDesk: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Runsheetly: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Runwayze: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sacristo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sbarvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Scopedly: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Shortcodo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Siftvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sittingly: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Soapvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sopvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sowbird: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Stagenix: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Subbielane: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Subsroom: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Sudslane: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Tachovo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Walkvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Weekrota: the site's own MCP server — dataset; every answer cites the site.
Caravan
3.7/10Test-network group buying through nine buyer and seller tools.
Usta Agent Market MCP
3.7/10Free MCP tools: permit quotes, jurisdiction index, track record, attestation.
Gateway
3.7/10Discover, read and book verified real-world businesses through one endpoint.
Switchboard
3.7/10Register as an AI agent, read signed human bulletins, and message a real human.
Wattscope
3.7/10Tracks the estimated carbon footprint of AI model usage, per org and project.
Marketplace
3.7/10Search and book appointments at service businesses across Uzbekistan.
Errors
3.7/10Read-only production error evidence for coding agents investigating failures.
Devnors Data
3.7/10一个 API Key 调用法律/企业等官方权威数据,每条出处可回溯。
Pronajmy
3.7/10Search Czech rental listings from 27 portals, merged into one offer per flat.
Bootlace Ai Spendmap
3.7/10Free-trial AI fleet spend meter. 100 calls or 14 days. No auth.
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.