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.
Isbn Uri
4.3/10ISBN URN shape, value discarded
Iso Unix
4.3/10ISO date to unix seconds, value discarded
Issn Uri
4.3/10ISSN URN shape, value discarded
Jsesc Ok
4.3/10JS escape sequence count, input discarded
Json Merge Ok
4.3/10JSON Merge Patch key count, body discarded
Json Min Ok
4.3/10JSON minify shape, body discarded
Json Ptr Ok
4.3/10JSON Pointer token count, path discarded
Json Type Ok
4.3/10JSON type-tag count, values discarded
Kebab N
4.3/10kebab-case segment count, value discarded
Keep Ok
4.3/10Keep-Alive timeout band, value discarded
Khz Mhz
4.3/10Kilohertz to megahertz, number discarded
Kml Ok
4.3/10KML Placemark count, body discarded
Kpa Bar
4.3/10Kilopascals to bar, number discarded
Ksuid Ok
4.3/10KSUID 27-char shape, value discarded
Lastmod Ok
4.3/10Last-Modified HTTP-date shape, value discarded
Ok
4.3/10ISO-8859-1 byte band, value discarded
Leap Sec
4.3/10Whether UTC day can have a leap second
Less Ok
4.3/10Less variable count, body discarded
Link Ok
4.3/10Link header relation count, value discarded
Loc Ok
4.3/10Location absolute-URL shape, value discarded
Lower Ok
4.3/10lowercase charset, value discarded
Ly Km
4.3/10Light-years to kilometers, number discarded
Mach Ms
4.3/10Mach number to m/s at STP, number discarded
Magnet Ok
4.3/10magnet: xt shape, value discarded
Len
4.3/10MD4 hex length, input discarded
Metro Len
4.3/10MetroHash hex length, input discarded
Mg G
4.3/10Milligrams to grams, number discarded
Mhz Ghz
4.3/10Megahertz to gigahertz, number discarded
Mi M
4.3/10Miles to meters, number discarded
Ml L
4.3/10Milliliters to liters, number discarded
Mmhg Kpa
4.3/10mmHg to kilopascals, number discarded
Month 1
4.3/10UTC first day of the current month
Month N
4.3/10UTC last day of the current month
Month Pad
4.3/10Days to pad current UTC month to 31
Multibase Ok
4.3/10multibase prefix charset, value discarded
Multihash Ok
4.3/10multihash prefix shape, value discarded
Len
4.3/10MurmurHash3 hex length, input discarded
Nanoid Ok
4.3/10nanoid URL-safe charset, value discarded
Ni Url
4.3/10ni: hash-URI shape, value discarded
Nix Ok
4.3/10Nix attr-set brace count, body discarded
Nm M
4.3/10Nanometers to meters, number discarded
Nmi Km
4.3/10Nautical miles to kilometers, number discarded
Obj Ok
4.3/10Wavefront OBJ vertex count, file discarded
Oid Arc
4.3/10ASN.1 OID arc shape, value discarded
Oz T G
4.3/10Troy ounces to grams, number discarded
Pa Kpa
4.3/10Pascals to kilopascals, number discarded
Para N
4.3/10paragraph-break count, text 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.