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.
Cc Tm
4.3/10Public ISO 3166-1 record for TM.
Cc Tn
4.3/10Public ISO 3166-1 record for TN.
Cc To
4.3/10Public ISO 3166-1 record for TO.
Cc Tr
4.3/10Public ISO 3166-1 record for TR.
Cc Tt
4.3/10Public ISO 3166-1 record for TT.
Cc Tv
4.3/10Public ISO 3166-1 record for TV.
Cc Tw
4.3/10Public ISO 3166-1 record for TW.
Cc Tz
4.3/10Public ISO 3166-1 record for TZ.
Cc Ua
4.3/10Public ISO 3166-1 record for UA.
Cc Ug
4.3/10Public ISO 3166-1 record for UG.
Cc Um
4.3/10Public ISO 3166-1 record for UM.
Cc Uy
4.3/10Public ISO 3166-1 record for UY.
Cc Uz
4.3/10Public ISO 3166-1 record for UZ.
Cc Va
4.3/10Public ISO 3166-1 record for VA.
Cc Vc
4.3/10Public ISO 3166-1 record for VC.
Cc Ve
4.3/10Public ISO 3166-1 record for VE.
Cc Vg
4.3/10Public ISO 3166-1 record for VG.
Cc Vi
4.3/10Public ISO 3166-1 record for VI.
Cc Vn
4.3/10Public ISO 3166-1 record for VN.
Cc Vu
4.3/10Public ISO 3166-1 record for VU.
Cc Wf
4.3/10Public ISO 3166-1 record for WF.
Cc Ws
4.3/10Public ISO 3166-1 record for WS.
Cc Ye
4.3/10Public ISO 3166-1 record for YE.
Cc Yt
4.3/10Public ISO 3166-1 record for YT.
Cc Za
4.3/10Public ISO 3166-1 record for ZA.
Cc Zm
4.3/10Public ISO 3166-1 record for ZM.
Cc Zw
4.3/10Public ISO 3166-1 record for ZW.
Ok
4.3/10IPv4 CIDR shape, value discarded
Ok
4.3/10IPv6 CIDR shape, value discarded
Cityhash Len
4.3/10CityHash hex length, input discarded
Clamp Ok
4.3/10Clamp n into [min,max], numbers discarded
Compose Ok
4.3/10Compose service count, body discarded
Composer Ok
4.3/10composer.json name shape, body discarded
Content Hash Ok
4.3/10Content-hash filename shape, name discarded
Cookie Name Ok
4.3/10Cookie name charset, value discarded
Cookie Token
4.3/10Cookie name charset, value discarded
Len
4.3/10CRC-16 hex length, input discarded
Csproj Count
4.3/10csproj package reference count, body discarded
Csproj Ok
4.3/10csproj package reference count, body discarded
Csr Fence
4.3/10CSR PEM fence check, body discarded
Css Rule Count
4.3/10CSS rule count, stylesheet discarded
Csv Cols Ok
4.3/10CSV header column count, rows discarded
Csv Header Ok
4.3/10CSV header count, body discarded
Shape
4.3/10CUID2 charset, value discarded
Data Uri Ok
4.3/10data: URI media-type only, payload discarded
De Plz
4.3/10German PLZ digit shape, value discarded
Der Ok
4.3/10DER sequence tag check, body discarded
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.