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.
Release To Tasks
4.1/10Convert public release-note URLs into ordered, source-cited upgrade tasks.
Lunchmoney App
4.1/10MCP-first access to your Lunch Money data.
MCP Ooxml Ledger
4.1/10Edit Office documents and prove no edit went unrecorded
Marzban MCP
4.1/10Manage Marzban panels through the Model Context Protocol.
Solana Snipe Bot MCP
4.1/10Autonomous Solana meme-coin sniper bot with 40 MCP tools for AI control.
Llm Preflight
4.1/10Local, cross-provider preflight checks for LLM integration changes.
Api Test MCP
4.1/10Call the real API and check the response against your OpenAPI spec.
Standup Mr
4.1/10Standup notes from merge request state, with the failed job's error lines.
Montycat MCP
4.1/10Shared, persistent memory for AI agents, with semantic recall and live updates.
Firefox Css Theme
4.1/10MCP for building, inspecting, and live-debugging Firefox CSS themes.
MCP Ollama Vllm
4.1/10Call your local Ollama or vLLM model over MCP with schema-validated JSON output
Sparda MCP
4.1/10AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
Policyvault
4.1/10Non-custodial Kaspa policy enforcement for AI agents; signers retain custody.
Kilawatt MCP Server
4.1/10Kilawatt Cloud MCP Server for AI Agent GPU Orchestration
Wrapguard MCP
4.1/10Detect unnatural Korean and English mid-word wrapping in responsive web pages.
MCP Cfdi Mx
4.1/10MCP server for Mexican electronic invoicing (CFDI 4.0, Pagos 2.0)
Knos
4.1/10The neutral meter for AI agent work: neither side keeps the count.
Fabricator Panel MCP
4.1/10Manage and diagnose Minecraft servers through the self-hosted Fabricator panel.
Mizuki
4.1/10Fixed-price maintenance for public GitHub issues, paid in USDC on Solana.
Cp Memory
4.1/10Local-first, governable long-term memory for AI coding agents
Rentctl
4.1/10Leased dev environments — every server dies when its AI session ends.
Memauthority
4.1/10Git-backed long-term memory authority for AI agents via MCP.
Caldav MCP
4.1/10A TypeScript MCP server for iCloud Calendar with native multi-VALARM support.
Asc MCP Server
4.1/10App Store Connect MCP Server for AI coding agents
Gpc MCP Server
4.1/10Google Play Console MCP Server for AI coding agents
Recraft MCP Server
4.1/10Recraft AI Image Generation MCP Server for AI coding agents
Samplemcp Server
4.1/10A sample MCP server that returns random weather descriptions.
Myatriumhealth MCP
4.1/10MyAtriumHealth (Epic MyChart) records via your signed-in browser tab
Weather
4.1/10An MCP server for weather information updating this value now.
Yunohost MCP
4.1/10Nostr-authenticated MCP server for secure YunoHost administration.
Coops MCP
4.1/10NOAA CO-OPS tides, water levels, currents, and meteorological data
Meok Annex Iii Impact MCP
4.1/10Automated EU AI Act Annex III risk classification and impact assessment engine
MCP Server
4.1/10Playwright-style MCP to inspect, control, and debug PySide6 desktop GUIs.
A2A To MCP
4.1/10A2A v1.0.1 agents as MCP 2026-07-28 tools, with the tasks extension
Meek Cfd Thermal MCP
4.1/10meek-cfd-thermal-mcp - MEOK science MCP for Project AURUM. MIT-licensed.
Orbit
4.1/10Orbit's local-first task and workflow registry for coding agents.
Hypelens Agent Rail
4.1/10Place/cancel/close HL perps via MCP. Agent wallet once, 1bp fills, no sub.
Atomic Clock
4.1/10Current UTC time from NTP atomic clocks. Zero-dependency stdio server.
Orcareplay
4.1/10Read, replay and fork recorded coding-agent runs.
Saudi Vat Pro
4.1/10Submit and manage ZATCA-compliant Saudi e-invoices through Saudi VAT Pro.
Wayfinder
4.1/10Read local AI coding paths, decisions, and branches as an in-host voyage map.
MCP Einvoicing In
4.1/10MCP server for India GST e-invoicing (FORM GST INV-01 schema v1.1 / IRP-IRN)
Razor
4.1/10Autonomous log surgery & secret redaction MCP server for AI coding agents.
Sudo Proxy
4.1/10Privileged command execution proxy with human approval via pkexec or sudo
Ris
4.1/10Access Austrian laws, court decisions & legal documents via the RIS API.
Claude Desktop Bridge
4.1/10Shared local knowledge vault MCP server for Claude Desktop (Chat + Code)
Clayseal
4.1/10Authorizes MCP tool calls against a session policy, not one call at a time.
Agentrender MCP
4.1/10URL to screenshot, PDF, or structured extract for AI agents via MCP.
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.