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 092
4.3/10Small public utility for autonomous clients.
Util 093
4.3/10Small public utility for autonomous clients.
Util 094
4.3/10Small public utility for autonomous clients.
Util 095
4.3/10Small public utility for autonomous clients.
Util 096
4.3/10Small public utility for autonomous clients.
Util 097
4.3/10Small public utility for autonomous clients.
Util 098
4.3/10Small public utility for autonomous clients.
Util 099
4.3/10Small public utility for autonomous clients.
Util 100
4.3/10Small public utility for autonomous clients.
Util 101
4.3/10Small public utility for autonomous clients.
Util 102
4.3/10Small public utility for autonomous clients.
Util 103
4.3/10Small public utility for autonomous clients.
Util 104
4.3/10Small public utility for autonomous clients.
Util 105
4.3/10Small public utility for autonomous clients.
Util 106
4.3/10Small public utility for autonomous clients.
Util 107
4.3/10Small public utility for autonomous clients.
Util 108
4.3/10Small public utility for autonomous clients.
Util 109
4.3/10Small public utility for autonomous clients.
Util 110
4.3/10Small public utility for autonomous clients.
Util 111
4.3/10Small public utility for autonomous clients.
Util 112
4.3/10Small public utility for autonomous clients.
Util 113
4.3/10Small public utility for autonomous clients.
Util 114
4.3/10Small public utility for autonomous clients.
Util 115
4.3/10Small public utility for autonomous clients.
Util 116
4.3/10Small public utility for autonomous clients.
Util 117
4.3/10Small public utility for autonomous clients.
Util 118
4.3/10Small public utility for autonomous clients.
Util 119
4.3/10Small public utility for autonomous clients.
Util 120
4.3/10Small public utility for autonomous clients.
Util 121
4.3/10Small public utility for autonomous clients.
Util 122
4.3/10Small public utility for autonomous clients.
Util 123
4.3/10Small public utility for autonomous clients.
Util 124
4.3/10Small public utility for autonomous clients.
Util 125
4.3/10Small public utility for autonomous clients.
Util 126
4.3/10Small public utility for autonomous clients.
Util 127
4.3/10Small public utility for autonomous clients.
Util 128
4.3/10Small public utility for autonomous clients.
Util 129
4.3/10Small public utility for autonomous clients.
Util 130
4.3/10Small public utility for autonomous clients.
Util 131
4.3/10Small public utility for autonomous clients.
Util 132
4.3/10Small public utility for autonomous clients.
Util 133
4.3/10Small public utility for autonomous clients.
Util 134
4.3/10Small public utility for autonomous clients.
Util 135
4.3/10Small public utility for autonomous clients.
Util 136
4.3/10Small public utility for autonomous clients.
Util 137
4.3/10Small public utility for autonomous clients.
Util 138
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.