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.
Unix Ms Ok
4.3/10Whether a number looks like unix milliseconds
Unix To Iso
4.3/10Unix seconds to UTC ISO, value discarded
Url Path Len
4.3/10URL path length, URL discarded
Url Path Ok
4.3/10URL path segment count, query discarded
Url Scheme Ok
4.3/10http/https scheme check, URL discarded
Url Slug Ok
4.3/10URL slug charset, value discarded
Util 001
4.3/10Small public utility for autonomous clients.
Util 002
4.3/10Small public utility for autonomous clients.
Util 003
4.3/10Small public utility for autonomous clients.
Util 004
4.3/10Small public utility for autonomous clients.
Util 005
4.3/10Small public utility for autonomous clients.
Util 006
4.3/10Small public utility for autonomous clients.
Util 007
4.3/10Small public utility for autonomous clients.
Util 008
4.3/10Small public utility for autonomous clients.
Util 009
4.3/10Small public utility for autonomous clients.
Util 010
4.3/10Small public utility for autonomous clients.
Util 011
4.3/10Small public utility for autonomous clients.
Util 012
4.3/10Small public utility for autonomous clients.
Util 013
4.3/10Small public utility for autonomous clients.
Util 014
4.3/10Small public utility for autonomous clients.
Util 015
4.3/10Small public utility for autonomous clients.
Util 016
4.3/10Small public utility for autonomous clients.
Util 017
4.3/10Small public utility for autonomous clients.
Util 018
4.3/10Small public utility for autonomous clients.
Util 019
4.3/10Small public utility for autonomous clients.
Util 020
4.3/10Small public utility for autonomous clients.
Util 021
4.3/10Small public utility for autonomous clients.
Util 022
4.3/10Small public utility for autonomous clients.
Util 023
4.3/10Small public utility for autonomous clients.
Util 024
4.3/10Small public utility for autonomous clients.
Util 025
4.3/10Small public utility for autonomous clients.
Util 026
4.3/10Small public utility for autonomous clients.
Util 027
4.3/10Small public utility for autonomous clients.
Util 028
4.3/10Small public utility for autonomous clients.
Util 029
4.3/10Small public utility for autonomous clients.
Util 030
4.3/10Small public utility for autonomous clients.
Util 031
4.3/10Small public utility for autonomous clients.
Util 032
4.3/10Small public utility for autonomous clients.
Util 033
4.3/10Small public utility for autonomous clients.
Util 034
4.3/10Small public utility for autonomous clients.
Util 035
4.3/10Small public utility for autonomous clients.
Util 036
4.3/10Small public utility for autonomous clients.
Util 037
4.3/10Small public utility for autonomous clients.
Util 038
4.3/10Small public utility for autonomous clients.
Util 039
4.3/10Small public utility for autonomous clients.
Util 040
4.3/10Small public utility for autonomous clients.
Util 041
4.3/10Small public utility for autonomous clients.
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.