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.
Peck L
4.3/10US pecks to liters, number discarded
Peg Ok
4.3/10PEG rule count, body discarded
Pipe N
4.3/10pipe-separated token count, value discarded
Pm M
4.3/10Picometres to meters, number discarded
Pole M
4.3/10Poles to meters, number discarded
Purl Gem
4.3/10pkg:gem package-url shape, value discarded
Purl Npm
4.3/10pkg:npm package-url shape, value discarded
Py Uesc
4.3/10Python unicode-escape count, input discarded
Q Mid
4.3/10UTC midpoint day of the current quarter
Rst Ok
4.3/10reStructuredText directive count, body discarded
Scrypt N
4.3/10scrypt N cost band, value discarded
Scsu Ok
4.3/10SCSU window-tag count, input discarded
Semi N
4.3/10semicolon-separated token count, value discarded
Server Ok
4.3/10Server product-token count, value discarded
Len
4.3/10SHA-1 hex length, input discarded
Sid Ok
4.3/10short-uuid sid charset, value discarded
Sip128
4.3/10SipHash-4-8 hex length, input discarded
Soap Ok
4.3/10SOAP Envelope shape, markup discarded
Srec Ok
4.3/10Motorola S-record count, input discarded
Svc Ok
4.3/10Alt-Svc h3 host:port shape, value discarded
Tei Ok
4.3/10TEI div count, markup discarded
Tiger160
4.3/10Tiger-160 hex length, input discarded
Tiger192
4.3/10Tiger-192 hex length, input discarded
Tk Ok
4.3/10Tk tracking status token, value discarded
Trig Ok
4.3/10TriG graph-brace count, body discarded
Ug G
4.3/10Micrograms to grams, number discarded
Ul L
4.3/10Microliters to liters, number discarded
Ulid Mod
4.3/10ULID monotonic counter bits, value discarded
Uml Ok
4.3/10UML XMI packagedElement count, markup discarded
Nb
4.3/10UTF-8 non-ASCII byte count, input discarded
Uuid B32
4.3/10UUID Crockford-32 shape, value discarded
Uuid B58
4.3/10UUID Base58 shape, value discarded
Via Http
4.3/10Via HTTP/1.1 hop count, value discarded
Ws Run
4.3/10whitespace run length band, text discarded
X Fwd Host
4.3/10X-Forwarded-Host hostname, value discarded
X Fwd Port
4.3/10X-Forwarded-Port integer band, value discarded
Xid B32
4.3/10XID Base32 charset, value discarded
Xid Hex
4.3/10XID 24-hex shape, value discarded
Xsd Ok
4.3/10XML Schema element count, markup discarded
128
4.3/10XXH3-128 hex length, input discarded
64
4.3/10XXH3-64 hex length, input discarded
Yacc Ok
4.3/10Yacc rule count, body discarded
Antlr Ok
4.3/10ANTLR grammar rule count, body discarded
Bbcode Ok
4.3/10BBCode tag count, body discarded
Cfm M3S
4.3/10Cubic feet/min to m3/s, number discarded
Cid Dagpb
4.3/10CIDv1 dag-pb codec prefix, value discarded
Content Loc
4.3/10Content-Location URL shape, value 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.