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.
Songcheck MCP
4.5/10Is this song AI or human? Detect AI-generated music (Suno, Udio) from any AI agent.
Akeyless Rta
4.5/10Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.
Pdfapi MCP Server
4.5/10Generate invoice, receipt, and report PDFs from structured JSON via a single API call.
Arxivsub MCP
4.5/10Search arXiv and major AI/ML/CV/NLP/robotics conference papers and their related work.
Generate Tech Stack
4.5/10Visual tech-stack inventory of any codebase: languages, frameworks, databases, AI SDKs, infra.
Workflow Generator
4.5/10Architecture diagram with concurrency capacity and bottleneck estimates from any codebase.
Easytable MCP
4.5/10easyTable restaurant reservations for Claude — availability, and create/modify/cancel bookings
Hashloom
4.5/10Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
Ecardwidget MCP
4.5/10Send eCards, run bulk campaigns, and automate recurring cards from your AI assistant.
Purify Feeds MCP
4.5/10Query CISA KEV / EPSS vulnerability feeds with full per-record provenance and auditable versions
Agentpack
4.5/10Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.
Zahori
4.5/10Find the media stream behind any web page: browser-driven HLS/DASH/MP4 with learnable site profiles
Code Atlas
4.5/10Multi-language code intelligence MCP server: symbols, call graphs, references, semantic search.
MCP Abap Abap Adt Api
4.5/10MCP server wrapping abap-adt-api for ABAP ADT development workflows against SAP systems
Datasaudi MCP
4.5/10Saudi economic & social statistics (GASTAT/DataSaudi) in English or Arabic. Keyless, no database.
MCP Me
4.5/10Expose your personal, professional, educational, and social profile to any AI assistant via MCP.
Prest
4.5/10Stdio MCP adapter bridging AI clients to pREST’s HTTP /_mcp endpoint for PostgreSQL APIs.
Ridvay MCP
4.5/10Create & edit Ridvay Studio posters, flyers & social designs — AI-generated or self-composed.
Agentrank MCP
4.5/10Find real, verifiable businesses with provenance and source URLs - for AI agents.
MCP Server Powerpoint
4.5/10PowerPoint automation for AI: slides, shapes, tables, charts, images, notes. Windows only.
Stillos Kya
4.5/10KYA: fail-closed CLEAR/REVIEW/BLOCK counterparty screen (OFAC + on-chain), signed receipt.
Payments Ai MCP
4.5/10Launch products and branded checkouts on Payments AI, the Merchant of Record for AI-built apps.
Citeguard
4.5/10Falsification-first citation auditor: existence, metadata, and claim-support checks via MCP.
Baton
4.5/10Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.
Braincloud MCP Helper
4.5/10Helper for brainCloud MCP that gives it local file access, enabling easy git sync of cloud code.
Nodeflare MCP
4.5/10Blockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call.
Macrofactor MCP
4.5/10Fueling & recovery decision engine combining MacroFactor nutrition with Garmin training data
Nodeflare MCP
4.5/10Blockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call.
Taskboard MCP
4.5/10Persistent task board synced across Claude Code and Claude.ai, backed by Supabase.
Robrain
4.5/10Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.
Resharper Cli MCP
4.5/10ReSharper CLI inspection/cleanup via MCP. Unofficial: not affiliated with or endorsed by JetBrains.
Roz MCP
4.5/10Roslyn-powered C# code navigation, blast-radius analysis, and verified edits for coding agents.
Kotlin Lib MCP
4.5/10Exposes the public API, KDoc and sources of Maven-published Kotlin/Java libraries to MCP clients
MCP Server Google Forms
4.5/10Cria, edita e publica Google Forms a partir do Claude: quizzes, seções e leitura de respostas.
Luca MCP
4.5/10Work your Luca workspace from any MCP client: 67 tools for leads, conversations, and campaigns.
Llm Provider MCP
4.5/10Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.
Ca Eli MCP
4.5/10MCP server for Canadian federal legislation (Justice Laws Website), verifiable citations.
Ch Eli MCP
4.5/10MCP server for Swiss federal legislation via Fedlex (native ELI), verifiable citations.
Cl Eli MCP
4.5/10MCP server for Chilean legislation via BCN Linked Open Data, verifiable citations.
Pk Eli MCP
4.5/10MCP server for Pakistani law: search and cite federal statutes and Supreme Court judgments.
Hscope
4.5/10Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.
Pineforge Backtest MCP
4.5/10Offline PineScript v6 → C++ backtests at deterministic TradingView parity, run locally via MCP.
Rancher MCP
4.5/10319 tools for Rancher-managed Kubernetes over MCP: discovery, generic access, operator workflows
Cochlea MCP
4.5/10Render, analyze, and verify audio (WAV/FLAC) offline and deterministically, exposed as MCP tools.
Fenestra MCP
4.5/10Render and verify native Rust GUIs headlessly: access tree, query, a11y, screenshots, motion.
X402 Facilitator Proxy
4.5/10Multi-tenant HTTP 402 infrastructure gateway and stdio MCP server for machine payments.
Evidence
4.5/10Evidence layer for agent commerce: signed receipts, verification, dispute evidence envelopes.
Myvideogift
4.5/10Create and deliver personalized video gifts (photos + an original song) from any agent.
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.