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.
Reportflow MCP
4.3/10Generate PDF reports from ReportFlow templates via Claude and other AI agents.
MCP Server
4.3/10AEO scoring, llms.txt audit, and agent-readiness checks for AI agents.
Leadbay MCP
4.3/10AI lead discovery, qualification, and outreach prep on your Leadbay account.
Unifi
4.3/10Safe-by-default UniFi MCP: Network + Protect, multi-site, dry-run, audit log.
Audit
4.3/10Score any public GitHub repo 0-100 against the commit.show audit rubric.
MCP Zap Server
4.3/10Safe, self-hosted OWASP ZAP operator for guided AI security scans and reports.
Cron Self Heal
4.3/10Watcher — surfaces crons in error state
Founder Letter Audio
4.3/10Renders a Cooper-edited founder letter to MP3 via ElevenLabs TTS
Gateway Pulse
4.3/10Probe Hermes/OpenClaw/Paperclip/Obsidian
Launchd Drift Recovery
4.3/10Watcher — kickstart -k drifted critical plists
Mrr Floor Check
4.3/10Daily Stripe MRR query against a configured floor
Skill Invocation Tracker
4.3/10Append-only telemetry helpers — track_start and track_end
Stale Gate Janitor
4.3/10Daily 04:00 CT housekeeping over data/approval-gates/
M Dev Tools MCP
4.3/10MCP server wrapping the m-dev-tools catalog: route_intent, describe, verify.
Neuraldraft MCP
4.3/10Neural Draft MCP — CMS, blog, bookings, galleries, commerce. 38 tools.
Colter
4.3/10MCP server for agentic commerce checks, fixes, Lens, tests, and Evidence Packs.
Spreadsheet MCP
4.3/10Agent-safe Excel workbook analysis, editing, recalc, and verification tools.
Clawops
4.3/10Deploy and manage self-hosted OpenClaw instances across clouds
Archy
4.3/10Architectural sensor for Python codebases.
Hilma MCP
4.3/10MCP server for Finnish public procurement notices (Hilma). Built by Aimiten.
Dr MCP
4.3/10Audits MCP configs, scores risk, and creates reversible repair plans.
Signet Eval
4.3/10Deterministic policy enforcement and MCP management for AI agent tool calls.
Local Ydb MCP
4.3/10Operate local-ydb deployments through local or SSH-backed MCP tools.
Nexus Legal
4.3/10International legal analysis (ISO 31000) across 31 jurisdictions — 11 tools.
Zaai Dev MCP
4.3/10Zaai Dev brand brief + captured design references for MCP-compatible AI tools.
Changedetection MCP
4.3/10MCP server for ChangeDetection.io website monitoring and change history.
Hermes Grocy MCP
4.3/10MCP server for Grocy household ERP inventory and shopping workflows.
Shiori MCP
4.3/10MCP server for Shiori bookmark management and tag workflows.
Wallabag MCP
4.3/10MCP server for wallabag read-it-later entries, tags, and annotations.
Nautilus Compass
4.3/10Drift-aware cross-agent memory · MCP/A2A · LongMemEval-S 56.6% · 1/15 Zep cost
Onto
4.3/10Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Gdd
4.3/10AI-controlled browser farm: N isolated Chromium instances with 36 MCP tools
Tokentrace
4.3/10Local-first AI CLI usage analytics for agents.
Sayba Skill Market
4.3/10Discover, invoke, publish, and rate AI Agent skills on Sayba platform
Aidance MCP
4.3/10Turn photos into realistic dance videos with AI motion transfer.
Aiphotoeditor MCP
4.3/10Best AI Photo Editor powered by GPT Image 2, Flux, Nano Banana & more.
Meigenai MCP
4.3/10Meigen AI is a curated meigen ai image prompt library.
Soorafr MCP
4.3/10Creez des images et videos exceptionnelles avec l'IA.
Tiramisu Ai MCP
4.3/10Tiramisu AI is an AI product. See the official site for full feature details.
Taype
4.3/10Control the TayPE desktop DAW locally via MCP.
Plant Genomics MCP
4.3/10Plant genomics MCP — 32 tools across 11 backends with cross-source synthesis.
MCP Broker
4.3/10Local MCP broker that exposes one compact entry for many upstream servers.
MCP Digger
4.3/10Progressive on-demand access to .NET NuGet package source for AI coding agents.
MCP Server
4.3/10Live AI compute pricing oracle — real-time LLM model prices across providers
Tapd MCP Server
4.3/10在 Cursor/Copilot 中查询、分析和回填 TAPD bug / 需求
Calories Club
4.1/10AI-powered calorie tracking with photo recognition, barcode scanning, and voice logging
Census Cbp
4.1/10Establishment counts, employment, and payroll by geography and NAICS code from Census CBP
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.