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.
Pushid Ts
4.3/10Firebase push-id time prefix, value discarded
Qencode Ok
4.3/10Q-encoding charset, input discarded
Quintal Kg
4.3/10Quintals to kilograms, number discarded
R K
4.3/10Rankine to kelvin, number discarded
Referrer Ok
4.3/10Referrer-Policy token, value discarded
Report To
4.3/10Report-To group count, body discarded
Resolv Ok
4.3/10resolv.conf nameserver count, body discarded
Rfc Errata Ok
4.3/10RFC errata id shape, value discarded
Ok
4.3/10encoded-word charset token, input discarded
Rison Ok
4.3/10Rison token charset, body discarded
Rod M
4.3/10Rods to meters, number discarded
Rpm Rad
4.3/10RPM to rad/s, number discarded
Scruple G
4.3/10Scruples to grams, number discarded
Sedol Ok
4.3/10SEDOL 7-char charset, value discarded
Sent Ok
4.3/10sentence-terminator charset, value discarded
Sentence N
4.3/10sentence-start cap count, text discarded
Set Cookie
4.3/10Set-Cookie attribute count, values discarded
Sexp Ok
4.3/10S-expression paren count, body discarded
Ok
4.3/10SHA-224 hex length, input discarded
224
4.3/10SHA3-224 hex length, input discarded
384
4.3/10SHA3-384 hex length, input discarded
Ok
4.3/10SHA-384 hex length, input discarded
Ok
4.3/10SHAKE128 hex length band, input discarded
Ok
4.3/10SHAKE256 hex length band, input discarded
Shiftjis Ok
4.3/10Shift_JIS lead-byte band, input discarded
Shot Ml
4.3/10Shots to milliliters, number discarded
Slash Ok
4.3/10slash-separated charset, value discarded
Slug Kg
4.3/10Slugs to kilograms, number discarded
Ok
4.3/10SM3 hex length, input discarded
Smile Ok
4.3/10Smile binary header, bytes discarded
Smime Ok
4.3/10S/MIME PKCS7 fence, body discarded
Snowflake Ts2
4.3/10Snowflake timestamp bits, value discarded
Sonyflake Ts
4.3/10Sonyflake timestamp bits, value discarded
Span Cm
4.3/10Spans to centimeters, number discarded
Ok
4.3/10SpookyHash64 hex length, input discarded
Sqid Alpha
4.3/10Sqids alphabet charset, value discarded
Sshcfg Ok
4.3/10ssh config Host count, body discarded
Stere M3
4.3/10Steres to cubic meters, number discarded
Stone Kg
4.3/10Stones to kilograms, number discarded
Streebog Ok
4.3/10Streebog-256 hex length, input discarded
Swid Ok
4.3/10SWID tagId charset, value discarded
Syslog Ok
4.3/10syslog PRI band, line discarded
Te Trailers
4.3/10TE trailers token, value discarded
Tfvars Ok
4.3/10tfvars assignment count, body discarded
Thrift Ok
4.3/10Thrift field-id count, body discarded
Ticker Ok
4.3/10ticker symbol charset, value discarded
Tiger Ok
4.3/10Tiger hex length, input 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.