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.
Edgarmcp
4.1/10Clean, normalized SEC EDGAR / FRED / ETF / index data for AI agents.
Cairn MCP
4.1/10Log Claude Code work sessions, file edits, and tasks to your Cairn account.
Pmb Ai
4.1/10Local-first persistent memory for AI coding agents.
Agent Security Lens
4.1/10MCP security trust-check for agents before installing MCPs, Skills or tools.
Clipgrab
4.1/10Save the system clipboard image to a PNG or JPG file for AI agents.
Routara MCP
4.1/10OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).
Network Aiops
4.1/10Governed network device ops (NAPALM) — 33 MCP tools with audit/undo.
Jsreverser MCP
4.1/10MCP server for JavaScript reverse engineering and browser debugging.
MCP Server
4.1/10MCP auth middleware: gate tool calls so only authorized agents can act.
Sdk
4.1/10TypeScript SDK for mutual ZKP authentication between humans and AI agents.
Shield
4.1/10Stdio MCP auth proxy: wrap any MCP server with per-tool permission enforcement.
MCP Nano Banana
4.1/10MCP server for Google Nano Banana (Gemini) image generation
MCP Pymupdf
4.1/10MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.
Google Drive Files MCP
4.1/10Minimal MCP server for Google Drive file management and Google Sheets editing.
Sorsa MCP
4.1/10MCP server for the Sorsa.io X/Twitter data API
Apiany MCP
4.1/10APIAny MCP server for model discovery, pricing, docs, and integration examples.
MCP Documentation Server
4.1/10Local-first document management and semantic search for AI coding agents
Elevenlabs MCP
4.1/10RunAPI MCP server for ElevenLabs: create tasks, poll status, check pricing.
Flux Kontext MCP
4.1/10RunAPI MCP server for Flux Kontext: create tasks, poll status, check pricing.
Kling MCP
4.1/10RunAPI MCP server for Kling: create tasks, poll status, check pricing.
Seedream MCP
4.1/10RunAPI MCP server for Seedream: create tasks, poll status, check pricing.
Suno MCP
4.1/10RunAPI MCP server for Suno: create tasks, poll status, check pricing.
Contest MCP
4.1/10Log amateur-radio QSOs to N3FJP logging software over its TCP API.
Inav MCP
4.1/10MCP server for iNAV flight-controller configuration and diagnostics
Gramps Web MCP
4.1/10MCP server for structured access to Gramps Web genealogy data
Adorbis MCP
4.1/10Adorbis AI MCP server. One key, 40+ models, auto-routed.
Dfxm Geo MCP
4.1/10MCP server for the dfxm-geo dark-field X-ray microscopy forward model
Capsule
4.1/10Compact, source-linked context packs that reduce token waste for coding agents.
Flux 2 MCP
4.1/10RunAPI MCP server for Flux 2: create tasks, poll status, check pricing.
Gemini Omni MCP
4.1/10RunAPI MCP server for Gemini Omni: create tasks, poll status, check pricing.
Gpt 4O Image MCP
4.1/10RunAPI MCP server for GPT-4o Image: create tasks, poll status, check pricing.
Gpt Image 2 MCP
4.1/10RunAPI MCP server for GPT Image 2: create tasks, poll status, check pricing.
Gpt Image MCP
4.1/10RunAPI MCP server for GPT Image: create tasks, poll status, check pricing.
Grok Imagine MCP
4.1/10RunAPI MCP server for Grok Imagine: create tasks, poll status, check pricing.
Hailuo MCP
4.1/10RunAPI MCP server for Hailuo: create tasks, poll status, check pricing.
Happyhorse MCP
4.1/10RunAPI MCP server for HappyHorse: create tasks, poll status, check pricing.
Ideogram V3 MCP
4.1/10RunAPI MCP server for Ideogram V3: create tasks, poll status, check pricing.
Imagen 4 MCP
4.1/10RunAPI MCP server for Imagen 4: create tasks, poll status, check pricing.
Infinitetalk MCP
4.1/10RunAPI MCP server for InfiniteTalk: create tasks, poll status, check pricing.
Luma MCP
4.1/10RunAPI MCP server for Luma: create tasks, poll status, check pricing.
Nano Banana MCP
4.1/10RunAPI MCP server for Nano Banana: create tasks, poll status, check pricing.
Qwen 2 MCP
4.1/10RunAPI MCP server for Qwen 2: create tasks, poll status, check pricing.
Recraft MCP
4.1/10RunAPI MCP server for Recraft: create tasks, poll status, check pricing.
Runway Aleph MCP
4.1/10RunAPI MCP server for Runway Aleph: create tasks, poll status, check pricing.
Runway MCP
4.1/10RunAPI MCP server for Runway: create tasks, poll status, check pricing.
Seedance MCP
4.1/10RunAPI MCP server for Seedance: create tasks, poll status, check pricing.
Topaz MCP
4.1/10RunAPI MCP server for Topaz: create tasks, poll status, check pricing.
Veo 3 1 MCP
4.1/10RunAPI MCP server for Veo 3.1: create tasks, poll status, check pricing.
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.