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.
MCP Server
4.7/10Create Elaan notification types, templates and brands, trigger sends, and debug delivery.
Rapprise
4.7/10Apprise notifications over MCP and CLI with authenticated stdio and HTTP transports.
Yarr
4.7/10Self-hosted media fleet operations across Sonarr, Radarr, Plex, and related apps over MCP and CLI.
Gateco
4.7/10Permission-aware retrieval for AI systems: policy-enforced access to organizational knowledge.
Vedetta
4.7/10x402 pay-per-call crypto sentiment, divergence & analyst reads. USDC on Base. NFA.
MCP Server
4.7/10Discovery client for Macaroon Network, an AI-agent marketplace paying via Lightning (L402).
MCP Server
4.7/10Profile, CV, jobs, compensation & application-tracking tools for AI agents, by rolnia.com.
Casemargin MCP Server
4.7/10Turn a support ticket into a structured case brief, or score its L2 escalation readiness.
Xcreener MCP
4.7/10Local stdio MCP bridge for XCREENER's XQL screener API — validate, explain, and run queries.
Permits
4.7/10SF Peninsula building permits and parcel buildability: SB 9, ADU and redevelopment leads.
Pagespeed Insights MCP
4.7/10One run is noise, so this reports the median of several distinct PageSpeed analyses and the spread.
Logi Approval
4.7/10logi Agent Approval Gate — human approval on the phone before high-risk agent actions.
Tashan
4.7/10Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.
Giveaway Raffle Winner Picker
4.7/10Pick giveaway and raffle winners nobody can rig — verifiable by anyone, no API key.
Mint
4.7/10Inspect Mac storage, explain file activity, and perform journaled cleanup with Trash and Undo.
Atono MCP Server
4.7/10Give your AI coding tools your team's product context: stories, bugs, epics, and glossary.
Mirastack Redfish MCP
4.7/10Governed MCP server for DMTF Redfish BMCs. Read-only by default; writes are opt-in and dry-run.
Devglow
4.7/10Start, stop, and inspect local dev servers in a desktop app instead of the agent's session.
Todoglow
4.7/10See what each of your coding agents is working on, and read or advance your todos.
Feedback Magic
4.7/10Create Feedback Magic widgets — feedback, surveys, changelog, roadmap — from your AI editor.
MCP Server
4.7/10Render HTML or templates to a hosted image, in one response. Free previews need no API key.
Tab
4.7/10Every tool a builder signs up for, on one tab: trials, burn, price drift. Local JSONL, zero deps.
MCP Server
4.7/10Risk score for a Base wallet before your agent pays it: 0-100, verdict and explained flags.
Ezstat MCP Server
4.7/10Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
MCP Server
4.7/10Make animated travel-route videos: plan a route, style the animation, render an MP4.
Ledger
4.7/10Tamper-evident action logging for agents: hash-chained append/verify, one JSONL file, zero deps.
Elicitly
4.7/10Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor
Libraryapi MCP
4.7/10US public libraries and branches near any address, with collections from the IMLS survey
Publicsafetyapi MCP
4.7/10US police, fire, EMS and hospital locations near any address, from federal HIFLD data
Hangar
4.7/10Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.
Marrow
4.7/10Read-only MCP access to your own Apple Health data, mirrored from the Marrow iOS app.
Netmon
4.7/10Query devices, alerts, syslog, NetFlow and metrics on your Netmon monitoring appliance.
MCP Server
4.7/10App Store Optimization data for AI agents: keyword ranks, scores, competitors, charts
Skilltotal
4.7/10Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
Svgrid
4.7/10Version-pinned Svelte 5 data grid APIs, 373 demo sources, and SvelteKit app scaffolding.
Viberevert
4.7/10Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Screenify
4.7/10Record your screen and export studio-styled demo videos on macOS, driven by your AI assistant.
Central Bank MCP
4.7/10Official central-bank & tax-authority exchange rates from 60+ institutions (ECB, Fed, BOJ, HMRC).
Video Extract MCP
4.7/10Download any video from a URL, or get its transcript and key frames. All local, no API keys.
Axon Emcp
4.7/10Official ℰMCP server for AXON — exposes 99 primitives, 34 templates, 30 examples to AI agents.
MCP Iyke
4.7/10Drive a running Ikenga desktop app from MCP clients — DOM, click, type, navigate, screenshot.
MCP Server
4.7/10Form backend that routes: one tool per Postbag API operation, plus quickstart and explain.
Altweb Context
4.7/10Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default.
Godai
4.7/10Automate the Godot Engine editor: edit scenes and scripts, run projects, manage engine versions
MCP Server
4.5/10Bring Kubit into your AI workflow — query your warehouse with natural language
Trust Intelligence
4.5/10Entity verification, sanctions screening, and trust scoring for AI agents.
Npm
4.5/10npm package trends and weekly downloads over time. Free key at trendsmcp.ai
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.