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.
Util 043
4.3/10Small public utility for autonomous clients.
Util 044
4.3/10Small public utility for autonomous clients.
Util 045
4.3/10Small public utility for autonomous clients.
Util 046
4.3/10Small public utility for autonomous clients.
Util 047
4.3/10Small public utility for autonomous clients.
Util 048
4.3/10Small public utility for autonomous clients.
Util 049
4.3/10Small public utility for autonomous clients.
Util 050
4.3/10Small public utility for autonomous clients.
Util 051
4.3/10Small public utility for autonomous clients.
Util 052
4.3/10Small public utility for autonomous clients.
Util 053
4.3/10Small public utility for autonomous clients.
Util 054
4.3/10Small public utility for autonomous clients.
Util 055
4.3/10Small public utility for autonomous clients.
Util 056
4.3/10Small public utility for autonomous clients.
Util 057
4.3/10Small public utility for autonomous clients.
Util 059
4.3/10Small public utility for autonomous clients.
Util 060
4.3/10Small public utility for autonomous clients.
Util 061
4.3/10Small public utility for autonomous clients.
Util 062
4.3/10Small public utility for autonomous clients.
Util 063
4.3/10Small public utility for autonomous clients.
Util 064
4.3/10Small public utility for autonomous clients.
Util 065
4.3/10Small public utility for autonomous clients.
Util 066
4.3/10Small public utility for autonomous clients.
Util 067
4.3/10Small public utility for autonomous clients.
Util 068
4.3/10Small public utility for autonomous clients.
Util 069
4.3/10Small public utility for autonomous clients.
Util 070
4.3/10Small public utility for autonomous clients.
Util 071
4.3/10Small public utility for autonomous clients.
Util 072
4.3/10Small public utility for autonomous clients.
Util 073
4.3/10Small public utility for autonomous clients.
Util 074
4.3/10Small public utility for autonomous clients.
Util 075
4.3/10Small public utility for autonomous clients.
Util 076
4.3/10Small public utility for autonomous clients.
Util 077
4.3/10Small public utility for autonomous clients.
Util 078
4.3/10Small public utility for autonomous clients.
Util 079
4.3/10Small public utility for autonomous clients.
Util 080
4.3/10Small public utility for autonomous clients.
Util 081
4.3/10Small public utility for autonomous clients.
Util 082
4.3/10Small public utility for autonomous clients.
Util 083
4.3/10Small public utility for autonomous clients.
Util 084
4.3/10Small public utility for autonomous clients.
Util 085
4.3/10Small public utility for autonomous clients.
Util 086
4.3/10Small public utility for autonomous clients.
Util 087
4.3/10Small public utility for autonomous clients.
Util 088
4.3/10Small public utility for autonomous clients.
Util 089
4.3/10Small public utility for autonomous clients.
Util 090
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.