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.
Nodeset MCP
4.1/10NodeSet MCP: parse OPC UA NodeSets, validate NodeIds, nodes and references.
Nwchem MCP
4.1/10NWChem MCP: parse inputs, validate blocks, geometry and task lines.
Odx MCP
4.1/10ODX MCP: parse diagnostic data, validate layers, containers and services.
Onix MCP
4.1/10ONIX MCP: parse book metadata, validate products, titles and identifiers.
Openioc MCP
4.1/10OpenIOC MCP: parse IOC bundles, validate indicators, conditions and content.
Openscap MCP
4.1/10OpenSCAP MCP: parse XCCDF and OVAL results, validate results, scores and ids.
Openvas MCP
4.1/10OpenVAS MCP: parse reports, validate findings, hosts, ports and severities.
Oracle Reports MCP
4.1/10Oracle Reports MCP: parse REX definitions, validate queries, groups and fields.
Orca MCP
4.1/10ORCA MCP: parse inputs, validate method lines, blocks and coordinates.
Osl Shader MCP
4.1/10OSL MCP: parse shader declarations, parameters, includes and closures.
Ossec MCP
4.1/10OSSEC MCP: parse rules, validate ids, levels, groups and descriptions.
Oval MCP
4.1/10OVAL MCP: parse definitions, validate ids, definitions and tests.
Pattern Grading MCP
4.1/10Grading MCP: parse grading rules, validate base size and increments.
Pepxml MCP
4.1/10pepXML MCP: parse search results, validate runs, spectrum queries and hits.
Phylip MCP
4.1/10PHYLIP MCP: parse alignments, validate taxa, site counts and names.
Plcopen MCP
4.1/10PLCopen MCP: parse TC6 XML, validate project root, POUs and types.
Ppml MCP
4.1/10PPML MCP: parse print jobs, validate jobs, documents and pages.
Quantum Espresso MCP
4.1/10Quantum ESPRESSO MCP: parse pw.x inputs, validate namelists and cards.
Rinex MCP
4.1/10RINEX MCP: parse GNSS observations, validate headers, epochs and satellites.
Rosettanet MCP
4.1/10RosettaNet MCP: parse PIP messages, validate headers, roles and line items.
Sage Accounting MCP
4.1/10Sage MCP: parse ledger exports, validate dates, debits, credits and totals.
Sbml MCP
4.1/10SBML MCP: parse models, validate compartments, species and reaction references.
Scorm MCP
4.1/10SCORM MCP: parse manifests, validate organizations, items and resource links.
Sdc MCP
4.1/10SDC MCP: parse timing constraints, validate commands, clocks and brackets.
MCP Server
4.1/10Seamly2D MCP: parse pattern XML, validate pieces, blocks and measurements.
Sfd MCP
4.1/10SFD MCP: parse FontForge sources, validate headers, characters and counts.
Shoe Size MCP
4.1/10Shoe Size MCP: parse EU/US/UK/JP tables and validate conversions.
Sibelius MCP
4.1/10Sibelius MCP: parse ManuScript plugins, validate blocks, functions and calls.
Size Chart MCP
4.1/10Size Chart MCP: parse body measurements, validate size labels and proportions.
Snomed Ct MCP
4.1/10SNOMED CT MCP: parse RF2 files, validate SCTIDs, columns and active flags.
Snort MCP
4.1/10Snort MCP: parse IDS rules, validate headers, actions, sids and revisions.
Spef MCP
4.1/10SPEF MCP: parse parasitics, validate units, nets, caps and resistances.
Srec MCP
4.1/10S-record MCP: parse Motorola records, validate counts, addresses and checksums.
Ssis MCP
4.1/10SSIS MCP: parse DTSX packages, validate executables, connections and variables.
Sudoers MCP
4.1/10sudoers MCP: parse sudo policy, validate aliases, user specs and command paths.
Tcx MCP
4.1/10TCX MCP: parse training files, validate activities, laps, time and distance.
Techpack MCP
4.1/10Tech Pack MCP: parse apparel tech packs, validate styles, sizes and quantities.
Temenos T24 MCP
4.1/10Temenos MCP: parse jBC source, validate program headers, inserts and END.
Tradacoms MCP
4.1/10Tradacoms MCP: parse interchanges, validate STX, END and segment counts.
Ufo Font MCP
4.1/10UFO MCP: parse .glif glyph files, contours, points and components.
Ukg Kronos MCP
4.1/10UKG MCP: parse timecard CSVs, validate employees, times and hours.
Unibasic Pick MCP
4.1/10UniBasic MCP: parse Pick BASIC source, validate headers and RETURN.
Upf MCP
4.1/10UPF MCP: parse power intent, validate commands, domains and braces.
Votable MCP
4.1/10VOTable MCP: parse astronomy tables, validate fields, datatypes and rows.
Vsam MCP
4.1/10VSAM MCP: parse IDCAMS definitions, validate clusters, keys and record sizes.
Waf MCP
4.1/10Waf MCP: parse wscript files, validate build functions and targets.
Wgl MCP
4.1/10WGL MCP: parse vectors, validate modules, signals and braces.
X12 837 MCP
4.1/10X12 MCP: parse 837 claims, validate ISA, ST/SE counts and claim segments.
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.