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.
Wan MCP
4.1/10RunAPI MCP server for Wan: create tasks, poll status, check pricing.
Z Image MCP
4.1/10RunAPI MCP server for Z Image: create tasks, poll status, check pricing.
Zyrax Guard
4.1/10Audit AI agent configs for prompt injection & rogue MCP servers; vet packages
Zdravo Cursor
4.1/10Persistent AI memory for Cursor. Save and search memories via Zdravo.
Brand Voice
4.1/10Enforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
Voicemode
4.1/10Natural voice conversations for AI assistants - STT/TTS via MCP
Ebay MCP
4.1/10eBay Browse API MCP server — buy-side listing search and price intelligence.
Memex
4.1/10Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Katatan Test
4.1/10KATATAN E2E testing agent set — Playwright + KATATAN MCP integration
Solfleet
4.1/10Agent-safe fleet management for independent Solana validators and RPC nodes
Wsjtx MCP
4.1/10Operate WSJT-X (FT8/FT4/WSPR) from MCP clients over its UDP message protocol.
Conduct Cli
4.1/10List agents, trigger workflows, and enforce team AI policies with ConductGuard.
Feed Reader
4.1/10Fetch and read RSS/Atom feeds from any MCP client.
Refinery MCP
4.1/10Clean raw HTML into LLM-ready text before agents spend tokens.
Graphlens MCP
4.1/10Semantic code graph MCP server for coding agents
Printscale MCP
4.1/10Upscale images to print-ready files (TIFF/PNG/JPG) via PrintScale.
Janusmcp
4.1/10Multi-account tool broker for AI agents — CLI and MCP.
Debt Payoff MCP
4.1/10RETIRED - this server is discontinued and its backend is offline. Do not use.
Etsy Tags MCP
4.1/10RETIRED - this server is discontinued and its backend is offline. Do not use.
Solrisk MCP
4.1/10RETIRED - this server is discontinued and its backend is offline. Do not use.
Docgen MCP Server
4.1/10Render HTML/markdown to PDF, export rows to xlsx, and fill AcroForm PDFs.
MCP Audit
4.1/10Scan, enumerate, and risk-score every MCP server configured on your machine.
MCP Trust
4.1/10Check the danger grade of any public MCP server before you connect.
Bridge MCP
4.1/10IBM i / RPG / DB2 bridge — parse, map, govern (IBM i security / SOX).
Healthpoint Rs
4.1/10Read-only MCP server for licensed Healthpoint HL7 FHIR API access.
Sqlbot MCP Proxy
4.1/10MCP server proxy for SQLBot Text-to-SQL queries and report generation.
MCP Cloudflare Dns
4.1/10Cloudflare DNS MCP server: manage zones, records, cache purge, and page rules.
Video Vision MCP
4.1/10Analyze any video (local file or URL) into frames + transcript for Claude Code
Manabuy MCP
4.1/10ManaBuy MCP server for product search, order quote, and AI-assisted ordering.
Aiiq MCP
4.1/10Query AI IQ (aiiq.org) model IQ, rankings, benchmarks, and methodology.
Godot Gut MCP
4.1/10Servidor MCP que permite ejecutar tests de Godot con GUT desde cualquier IA
Proton Workflow Connector
4.1/10Unofficial self-hosted MCP connector for Proton Mail Bridge and SimpleLogin.
Resourceguru MCP
4.1/10Operate Resource Guru from your AI agent via MCP.
Sk Eli MCP
4.1/10MCP server for Slovak legislation (Slov-lex) with ELI and verifiable citations.
Arcgis MCP Bridge
4.1/10Secure local-first MCP server for licensed ArcGIS Pro and ArcPy on Windows.
Salonrunner MCP
4.1/10Self-hosted MCP to find, book, and cancel salon appointments via SalonRunner.
Opendaw MCP
4.1/10262 MCP tools for agent-native control of openDAW, a browser-based DAW
Shotflow MCP
4.1/10ShotFlow MCP Server — AI分镜脚本与视频生成智能体，支持生成专业分镜、视频、镜头重生成、配额查询等能力。
Mediamcp
4.1/10Generate and edit images and video via OpenRouter or any OpenAI-compatible API.
Multichain MCP
4.1/10MCP server for AI agents — Stacks, Celo, and Base in one npm package.
Sparda MCP
4.1/10AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
Blast Scope
4.1/10Contextual blast-radius scoring for shell commands an AI agent is about to run
MCP Server
4.1/10PayFlowAgent suite: token intel, DeFi, enrich, Base trust (x402).
Atlassian Dc MCP Confluence
4.1/10MCP server for Atlassian Confluence Data Center - access and manage content
Atlassian Dc MCP Jira
4.1/10MCP server for Atlassian Jira Data Center - search, view, and create issues
Personal MCP
4.1/10An MCP server that provides [describe what your server does]
MCP Pagbrasil
4.1/10PagBrasil — cross-border acquiring into Brazil: Pix, Boleto Flash, refunds
X402 Ads MCP
4.1/10x402 ad recommendations, intent analytics, and machine-commerce demand reports.
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.