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.
Nx MCP
4.1/10A Model Context Protocol server implementation for Nx
Rival
4.1/10Query AI model benchmarks, pricing, and comparisons from rival.tips
Tablestakes
4.1/10Read and edit HTML/Markdown tables in GitBook-synced documents via MCP tools.
Ai Context Kit
4.1/10Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
Devutils
4.1/10Developer utilities MCP: base64, UUID, hash, JWT decode, cron, timestamps.
Github Actions
4.1/10GitHub Actions MCP — view runs, read logs, re-run jobs, and manage CI/CD.
Github Gist
4.1/10MCP server to create, read, update, list, and search GitHub Gists from your IDE
Markdown
4.1/10Markdown MCP — search, extract sections, list headings, find code blocks.
Npm Plus
4.1/10npm MCP — search packages, bundle sizes, vulnerabilities, compare downloads.
Npm Search
4.1/10npm search MCP — find packages, view details, compare, check downloads.
Real Browser
4.1/10MCP server + Chrome extension for AI browser control with real sessions.
S3
4.1/10AWS S3 MCP — list buckets, browse objects, upload/download, presigned URLs.
Scraper
4.1/10Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Sqlite
4.1/10SQLite MCP — query databases, inspect schemas, explain queries, export data.
Hostinger Ssh MCP
4.1/10MCP server for connecting Claude Code to a Hostinger VPS via SSH
Simple MCP
4.1/10A Test MCP server that provides tools, promts and resources
Miro MCP Server
4.1/10Control Miro whiteboards with AI. 77 tools for boards, diagrams, mindmaps.
Nordic Registry MCP Server
4.1/10Access Nordic business registries (Norway, Denmark, Finland, Sweden). 23 tools.
Core
4.1/10Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Xap
4.1/10Agent settlement protocol — discover, negotiate, settle, and verify with XAP.
Onelogin MCP
4.1/10MCP server for OneLogin API - manage users, apps, roles, and authentication
MCP Console Automation
4.1/10MCP server for AI-driven console application automation and monitoring
MCP Prowl
4.1/10Discover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics.
Openfuse MCP
4.1/10Encrypted mail, shared memory, and persistent context for AI agents.
Ziti MCP Server
4.1/10Manage OpenZiti zero-trust networks — through natural language
Fascia MCP Server
4.1/10Expose Fascia-deployed Tools and Entity schemas to AI agents via MCP
Originalvoices
4.1/10MCP server for OriginalVoices - Ask AI twins questions about any audience
Gitlab Docs
4.1/10GitLab documentation search for AI assistants via Model Context Protocol (MCP)
Cantrip
4.1/10MCP server for Cantrip — AI-powered GTM engine for solo founders
Symbols
4.1/10MCP server to read, inspect and troubleshoot codebase symbols
Pforge
4.1/10Zero-boilerplate MCP server framework with declarative YAML configuration
Smara
4.1/10Persistent cross-platform memory for AI agents with Ebbinghaus decay scoring.
Odoo MCP Gateway
4.1/10Security-first MCP gateway for Odoo 17/18/19 — YAML-driven security, 27 tools
Specrun
4.1/10MCP server that converts OpenAPI specs into tools which can query API endpoints
Pay MCP
4.1/10USDC payments for AI agents on Base — direct, tabs, x402 paywalls, discovery
Paypal MCP Server
4.1/10A command line tool for setting up PayPal MCP server
Neemee MCP
4.1/10MCP client library and bridge for Neemee personal knowledge management system
Pqvault
4.1/10Post-quantum secrets manager for AI agents. ML-KEM-768 + X25519 + AES-256-GCM.
MCP Server Colab Exec
4.1/10Execute Python code on Google Colab GPU runtimes (T4/L4) from any MCP client
MCP Server
4.1/10Token intelligence on Base. Market data, safety flags, and analysis via x402.
Anneal Memory
4.1/10Two-layer memory for AI agents with an immune system. Zero dependencies.
Openharness
4.1/10Lets AI coding agents discover and reference each other's recent sessions.
Ris
4.1/10Access Austrian laws, court decisions & legal documents via the RIS API.
MCP Gsc
4.1/10Google Search Console MCP server — query performance, sitemaps, indexing & more
MCP Redtrack
4.1/10MCP server for RedTrack affiliate tracking API
MCP Sanity Images
4.1/10MCP server for uploading local images to Sanity CMS
MCP Datalink
4.1/10MCP server for secure database access (PostgreSQL, MySQL, SQLite)
Pinchwork
4.1/10Agent-to-agent task marketplace with credit escrow and reputation tracking.
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.