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.
Pagebolt
4.5/10Screenshots, PDFs, OG images, page inspection, and narrated video recording for Claude and Cursor.
Botindex MCP Server
4.5/10DeFi signal intelligence + agent discovery. Funding arb, whale alerts, Zora, compliance.
Llm Advisor
4.5/10Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
Cortex
4.5/10Local repo context for coding assistants with semantic search and graph relationships.
Repomemory
4.5/10Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
Github
4.5/10MCP server for GitHub operations (PRs, issues, actions) with structured, token-efficient output
Pare Build
4.5/10Pare Build ג€” Structured build output (tsc, esbuild, vite, webpack) as typed JSON diagnostics.
Pare Cargo
4.5/10Pare Cargo ג€” Structured Rust cargo operations (build, test, clippy, fmt, doc) as typed JSON.
Pare Docker
4.5/10Pare Docker ג€” Structured Docker operations (ps, images, logs, build, compose) as typed JSON.
Pare Git
4.5/10Pare Git ג€” Structured git operations (status, log, diff, branch, commit, push) as typed JSON.
Pare Github
4.5/10Pare GitHub ג€” Structured GitHub operations (PRs, issues, actions) as typed JSON.
Pare Go
4.5/10Pare Go ג€” Structured Go tool output (build, test, vet, fmt, mod) as typed JSON diagnostics.
Pare Http
4.5/10Pare HTTP ג€” Structured HTTP request operations (GET, POST, HEAD) as typed JSON.
Pare Lint
4.5/10Pare Lint ג€” Structured linting and formatting (ESLint, Prettier, Biome, Oxlint) as typed JSON.
Pare Make
4.5/10Pare Make ג€” Structured Make/Just task runner operations (run, list) as typed JSON.
Pare Npm
4.5/10Pare npm ג€” Structured npm/pnpm operations (install, audit, outdated, list, run) as typed JSON.
Pare Python
4.5/10Pare Python ג€” Structured Python tool output (ruff, mypy, pip, uv, black, pytest) as typed JSON.
Pare Test
4.5/10Pare Test ג€” Auto-detects test framework (pytest, jest, vitest, mocha), returns typed JSON.
Python
4.5/10Structured Python tool output (ruff, mypy, pip-audit, pip-install) as typed JSON.
Search
4.5/10MCP server for code search (ripgrep + fd) with structured, token-efficient output
Test
4.5/10Auto-detects test framework (pytest, jest, vitest) and returns structured results.
Rollin MCP Server
4.5/10Wheelchair accessibility scores for 70,000+ US restaurants. Search, filter, and submit feedback.
Nace MCP
4.5/10Browse, search and fuzzy-match NACE Rev. 2.1 economic activity classification codes.
Hal
4.5/10HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models
MCP Web Scraper
4.5/10Enable your AI agents to scrape and parse web content dynamically, including geo-restricted sites
Agentbuilders
4.5/10Deploy full-stack AI agent apps with database, auth, storage, and Edge AI on one platform.
Ddc Ci Control Bridge
4.5/10Control monitor brightness, contrast, power and input via DDC/CI with MCP and MQTT support.
Shadowcrawl
4.5/10Rust MCP stealth scraper: anti-bot search/scrape with CDP fallback + HITL non-robot.
Fulcrum
4.5/10AI governance MCP server for policy enforcement, cost control, and observability.
Ts MCP Debugger
4.5/10Enterprise debugging for Node.js/TypeScript with 25+ tools: breakpoints, profiling, hang detection
Dingdawg Compliance
4.5/10EU AI Act + Colorado AI Act compliance scoring. 87/100 in 60 seconds. Free local scan.
Dingdawg Finance Agent
4.5/10Financial analysis AI. Forecasting, audit prep, SOX/GAAP compliance. Accuracy compounds with use.
Dingdawg Healthcare Agent
4.5/10HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.
MCP Server
4.5/10OSS to create Personas, Skills, Templates, Agents, and Memories to customize your AI experience.
Infracost
4.5/10MCP server for Infracost CLI integration - cloud cost estimates for Infrastructure as Code
Gunsnation
4.5/10MCP server for real-time access to the Gunsnation firearms catalog and specifications.
Locus
4.5/10Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
Easysend
4.5/10EasySend file sharing MCP server - upload, download and share files. No authentication required.
Paper Distill MCP
4.5/10Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support.
Source Library
4.5/10Search 22,000+ rare pre-modern texts with AI English translations, summaries, and 73K+ images.
Voidly MCP Server
4.5/1083 tools: censorship intelligence (119 countries) + E2E encrypted agent messaging
Preflight Ios MCP
4.5/1057 tools for AI-powered iOS Simulator automation — tap, swipe, type, screenshots, and more.
Koa Fhe
4.5/10Confidential coprocessor — compute on encrypted data via FHE. Server never sees plaintext.
Ordinals
4.5/10Bitcoin Ordinals MCP Server — inscriptions, runes, BRC-20, collections & rare sats
Photo Organizer
4.5/10AI-powered organization for Google Photos and Drive - auto-organize, find duplicates, create albums
Solmail
4.5/10Send physical mail with Solana cryptocurrency - AI agents can send real letters worldwide
Sui MCP Server
4.5/1053-tool MCP server for Sui blockchain — wallets, DeFi, Move contracts, staking, SuiNS, analytics
Bitbucket MCP
4.5/10Bitbucket Cloud MCP in Go: complete API auto-generated from spec, customizable prompts.
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.