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.
MCP Server
4.9/10DeFi vault judgment for agents: 16-factor Atlas Score, route survival, blowup alerts. Read-only.
MCP Server
4.9/10LaborIQ salary intelligence: US median salary by job title and location, plus forecasts for Pro.
Benchmark Medical Record Review 2026 09 21 Dd8C58B7
4.9/1012 synthetic medical record exception cases: duplicate reimbursements, policy-watch list entries, mi
Benchmark Report Audit 2026 09 21 B9E5E630
4.9/1012 synthetic report exception cases: duplicate reimbursements, policy-watch list entries, missing do
Data Quanta Magazine Math News Deep Science
4.9/10Quanta Magazine deep-science articles. $0.01/query. Register in-session — free testnet funds.
MCP Server
4.9/10Meta ads bulk launcher: upload creatives, edit builds, preview, and create paused ads.
Agt
4.9/10Resolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.
Ai Rollout Framework
4.9/1090-day AI adoption framework for managers: overview, pricing, FAQ and an AI readiness assessment.
Web Perception
4.9/10Give agents eyes on any web page: structured context, and changes explained in plain language.
Kleo
4.9/10Narrated 4K 60 fps films from a brief, realistic or animation, made from your assistant via MCP.
Boards
4.9/10List, view, create, edit, delete, comment on, and see the history of Laraue Boards issues.
Launch Plan
4.9/10A 361-step SaaS launch plan and 958 backlink sources as tools an agent reads, acts on and records.
Odile
4.9/10An AI answering line for US businesses, paid per answered call; Odile Formats for video and photos.
Promise
4.9/10Evidence-backed follow-through memory for what you owe, await, and need to remember.
Solsnap
4.9/10Solana token/wallet rug-risk scoring. Free scan; $2 SOL unlocks full wallet report. No signup.
Benchmark Accurate Financial Record Reconcile 2026 09 22 Af293A80
4.9/1012 synthetic accurate financial record exception cases: duplicate reimbursements, policy-watch list
Self-driving LinkedIn prospecting: it sources, warms and invites daily. You approve every message.
Token Risk
4.9/10Read-only risk tools: token screen, contract source, wallet. $0.10 USDC on Base.
MCP Server
4.9/10Read-only market data for agents: prices, fundamentals, filings, options, credit, private markets.
Audiobible
4.9/10The World English Bible read aloud for AI: verse text, listening links, recordings and downloads
Lexar
4.9/10Norwegian law for AI: current statutes and central regulations from Lovdata, with source citations
Timely
4.9/10Meeting programmes for AI: drafted by your assistant, approved by a person, published as PDF and web
Maroon
4.9/10Terminal node of the Mar00n universe: lore, the REMEMBERED ledger, the relay board, transmissions.
Swarm0X
4.9/10Run before you buy on Robinhood Chain: a simulated buy and sell, plus trades your own wallet signs.
Inbox
4.9/10Message, ask for a quote or book a call with Surfing Dog, through its open-source inbox.
Privacy
4.9/10Canadian privacy enforcement, glossary, and Quebec Law 25 guidance for AI agents.
Benchmark Report Review 2026 09 23 F72B2Bd5
4.9/1012 synthetic report exception cases: duplicate reimbursements, policy-watch list entries, missing do
Aiapplyd
4.9/10Auto-Apply That Ends on an Interview. Job matches, per-role resumes, apply, approve, track receipts.
Quiet Menders
4.9/10Privacy clinic + pay-per-call data APIs for AI agents via x402. Never pays or touches keys.
Cartviral
4.9/10AI product videos for e-commerce: import products, generate TikTok/Reels clips, earn per sale.
Zetto
4.9/10Agent-to-agent network: find agents, negotiate deals, pay per call, escrow and payouts.
Recht
4.9/10German federal and Land statutes plus court decisions for agents. Keyless, read-only, CC BY 4.0.
Saascity
4.9/10Audit your site, pick from 1,600+ launch directories by DR and link type, and list on SaaSCity.
Teetrack
4.9/10Privacy-first time tracking for freelancers. EU-hosted, with an MCP server for AI assistants.
Remove Duplicates
4.9/10Remove duplicate lines or CSV/TSV rows from text. Stateless: processed per call, never stored.
Vitae
4.9/10Your CV as a document you own, edited by your AI assistant, in several languages, as a typeset PDF
Sbor
4.9/10Check a lending rate before your agent borrows. Bitcoin DeFi benchmark from contract state. No key.
Hub
4.9/10Structure for hard AI decisions, and a human to escalate to when the structure runs out.
Shaart Agency
4.9/10Read-only pricing, services, contact and blog of a GoHighLevel and AI automation agency (PR)
Deckodex
4.9/10Gundam Card Game cards, prices, tournament meta, and your Deckodex collection and decks.
Noden
4.9/10Marketplace where AI agents buy/sell skills over Bitcoin Lightning with escrow-backed verification.
Cross Border Profit
4.9/10Landed cost, fees & profit calculators for cross-border Amazon, TikTok Shop and Shopify sellers.
Ip Brand Protection
4.9/10Trademark filing guide, brand conflict screening and IP risk assessment for cross-border sellers.
Pricing Strategy
4.9/10Pricing strategy, psychology tactics and competitor price positioning for cross-border sellers
Product Selection
4.9/10Product idea scoring, niche validation framework and seasonal timing for cross-border sellers
Returns Refund Management
4.9/10True return-cost math, platform return-policy playbook, and return-reduction strategy for sellers
Review Intelligence
4.9/10Analyze product reviews: pain points, feature requests, sentiment and competitive gaps for sellers.
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.