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.
Bodymeasure
4.1/10Anthropometric predictions and percentile lookups via the Humanform API.
Citesearch
4.1/10Search, read and trace links across the Edgepedia encyclopedia corpus.
Cloudsession
4.1/10Local AWS session and execution-plan state as MCP tools.
Docmark
4.1/10Convert documents and URLs to Markdown via the hosted file2markdown service.
Familyorg
4.1/10Cozi family members, lists and shared calendar, as MCP tools.
Linkguard
4.1/10Forward URL safety scans to the hosted PreClick remote MCP endpoint.
Matrixshrink
4.1/10Finds redundant CI matrix combinations from run history and coverage overlap.
Notifyfan
4.1/10Apprise notification fan-out: health, status, and tagged or one-off sends.
Packcompare
4.1/10Diff two versions of a package: files, dependencies, size, and exports.
Partnerloop
4.1/10CreationLoop design partners: company overview, partner offer, FAQ, and apply.
Prbody
4.1/10Build a PR body from its commits, the linked issue, and the repo's PR template.
Prepboard
4.1/10Calaf seeds core subset (4 of 38): format, validate, import, list workspaces.
Scanverdict
4.1/10Local stdio bridge to GroundTruth scan reads, bid drafts and pricing.
Tellcheck
4.1/10Voice-style checks and a deterministic AI-tell audit for your writing.
Topiclint
4.1/10Sparkplug B topic linting and UNS naming checks for MQTT topic paths.
Wattprice
4.1/10Fetch PVPC electricity prices from Spain's ESIOS API by date range and area.
Yapi MCP
4.1/10Fetch YApi JSON API docs from a project URL for agent client integration.
Deckwright
4.1/10Inspect PowerPoint slide state, timelines, Morph links, and package findings.
Agentmesh
4.1/10Discover and call remote MCP tools as your own authenticated Agent Mesh member.
Kivio MCP Creator
4.1/10Upload AI videos, manage series, handle commissions, see earnings on KiVio.
Beans MCP
4.1/10Interact with the Beans CLI issue tracker agentically
MCP Pfsense
4.1/10Manage pfSense firewalls through AI assistants — rules, DHCP, DNS, and more
MCP Proxmox
4.1/10Manage Proxmox VE clusters through AI assistants — VMs, containers, and more
Forgingstack Mandate Check
4.1/10Before your agent acts, check its mandate. One call, one receipt.
Amr MCP
4.1/10Antimicrobial resistance genes, sequences and literature from NCBI and UniProt
Discord MCP
4.1/10A community MCP server for the Discord REST API with traceable coverage
Domstrip MCP
4.1/10Turn any web page or raw HTML into compact, clean Markdown for AI agents.
Porefind
4.1/10Search lab-filtration products by specification, with prices and lead times.
Ghostbus
4.1/10Agent-to-agent message bus and shared workspace, exposed as an MCP server.
Apache Aiops
4.1/10Governed Apache HTTP Server operations — 17 MCP tools with audit.
Aiops
4.1/10Governed BIND 9 DNS operations — 23 MCP tools with audit.
Harbor Aiops
4.1/10Governed Harbor registry operations — 39 MCP tools with audit.
Dmt Receipts
4.1/10Prepare and verify TAP/Ordinals payloads for AI agent memories on Bitcoin.
Ruff Lint X402
4.1/10Ruff Python linting for AI agents, pay-per-call via x402 ($0.005 USDC on Base).
Multigres MCP
4.1/10Postgres diagnostics and cluster operations for Multigres clusters.
Ssh Fleet MCP Server
4.1/10MCP server that manages a fleet of SSH hosts via pooled connections.
Linq
4.1/10Send and manage iMessage, RCS, and SMS conversations through the Linq API.
Dmt Receipts
4.1/10Stamp and verify Bitcoin-anchored OpenTimestamps memory receipts for AI agents.
Proceed MCP
4.1/10Preview Telegram approval broker for MCP clients; live first use unverified.
MCP Us Import Records Buyer Finder
4.1/10US importers and suppliers from customs bill of lading records, by company name
Symantec Clouddlp Aiops
4.1/10Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
Symantec Dcs Aiops
4.1/10Governed Symantec DCS operations — 35 MCP tools, read-only with audit.
Symantec Edr Aiops
4.1/10Governed Symantec on-prem EDR — 20 MCP tools, read-only with audit.
Symantec Ztna Aiops
4.1/10Governed Symantec ZTNA operations — 40 MCP tools, read-only with audit.
Proofmark Clock
4.1/10Current time in any time zone, and conversion of a date-time between zones.
Proofmark Demo Server
4.1/10A small filesystem MCP server used to demonstrate Proofmark attestation.
Proofmark Hash
4.1/10Hash text with SHA-256, SHA-512 or SHA3-256, and verify a digest.
Proofmark Units
4.1/10Convert between units of length, mass, temperature and data size.
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.