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.
Inbio
4.9/10Official in.bio MCP server: shorten URLs, styled QR codes, and click analytics. No API key needed.
Mcplint
4.9/10Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Friday Seller Tools
4.9/10Marketplace-seller tools: listing audits, PPC kits, pricing, compliance. Paid via x402 or card.
Casenode Legal Graph
4.9/10UK case law MCP (21 tools). Free API key: casenode.ai/api/signup → Dashboard → API keys.
Voc MCP
4.9/10VOC OpenAPI gives AI agents authorized review and product data for insights, tagging, and listings.
Statcite
4.9/10Cited economic statistics: World Bank, IMF, BIS, ECB, Caribbean central banks. Verify any figure.
Posterly
4.9/10Validate, schedule, publish, and analyze social content across 18 platforms with posterly.
Nyc Restaurant Week MCP
4.9/10All 636 NYC Restaurant Week Summer 2026 restaurants — filter by cuisine, borough, price, and date.
Ads MCP
4.9/10Run Google, Meta, Microsoft, TikTok and LinkedIn Ads from Claude or ChatGPT. Writes need approval.
Regulatory Catalysts
4.9/10Regulatory Catalysts MCP — high-value biotech regulatory calendar events (keyless).
The Hill Kinabalu
4.9/10Official rooms, live availability, booking links, and wedding info for The Hill Kinabalu.
Uizze
4.9/10UI design that stands out. Full-screen UI references and design materials for coding agents.
Profile MCP
4.9/10Read-only MCP profile server: CV, case studies, claim-to-evidence map, and role matching.
MCP Catalog
4.9/10AI-native corporate gifting & event infrastructure for Fortune 500. 70K products, 200+ brands.
Parlayapi
4.9/10Sports odds, player props and source coverage for AI assistants. Connect with your own API key.
Mesh Connector
4.9/10The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.
MCP Server
4.9/10Deterministic axe-core accessibility scans (WCAG 2.1 AA, EN 301 549, PDF/UA) via your account.
Bilinc
4.9/10Hosted agent memory with provenance, contradiction surfacing, and snapshot rollback.
Studiepoint Ai
4.9/10300+ African scholarships, GPA conversion & 1,700+ visa routes for postgrad students.
Geo MCP
4.9/10Free GeoNames MCP: countries, cities, POIs, distance & nearby. Remote HTTP + agent token signup.
Marigold
4.9/10Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.
Tools For Agents
4.9/10Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
Tnt House Risk Data Api
4.9/10RiskDataApi — Solana token risk scoring for AI agents. Safety score, insider clusters, honeypot.
Corpus
4.9/10Cite the claim, not the paper: 5,033 assertions, each hash-verifiable against its source PDF
MCP Server
4.9/10Run your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post.
Kit Memory Demo
4.9/10Continuity for agents: a live memory you can read and cite right now, outliving the context window.
Saightly
4.9/10Svensk marknadsplats för lokala tjänster från verifierade företag — sök, boka och begär offert.
Oddsockets
4.9/10Agent-first real-time messaging: pub/sub, presence, history. 12 tools over SSE, self-provision.
Prompt Compass
4.9/10Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
Fudge
4.9/10Build websites that look designed, not generated. Fudge gives AI real websites to study.
Finddoc
4.9/10GTA doctor, specialist, clinic, language, availability, and freshness data through REST and MCP.
MCP Server
4.9/10Agentic code review, no signup to try: reality gates + frontier-model review, with veto.
Dead Simple Email
4.9/10Give an agent its own inbox: send, receive, and pull signup codes from real email.
Stellary Project Management
4.9/10Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
Agent Pulse
4.9/10Action-required AI dependency changes and tested tools with reproducible evidence.
Vitamind
4.9/10Know when the sun can make vitamin D where you are, for your skin type. Live UV data.
Certvas
4.9/10License-clean African & EM data as citable agent tools: company fundamentals, tenders (OCDS), macro.
Websiteiq
4.9/10Robots-aware website audits, pre-crawl quotes, and structured evidence for people and agents.
Fulcru
4.9/10Find where ChatGPT names your competitor, write the page that closes the gap, measure it.
Agent Handoff
4.9/10Pass messages between AI agents with cleaning, metadata enrichment, and metered billing.
Trimtab Ais
4.9/10US tariff & trade truth: duty actually paid by origin/HS 2017+, HTS rulebook, CBP rulings. No key.
Ecommerce Prompts MCP
4.9/10Free copy-and-run ChatGPT prompts for online stores: 924 prompts, 43 categories + 10 tasks.
Gateway
4.9/10Per-call data for agents: graded behavioural science, dark-pattern detection, web fetch, geocode.
Clearlist
4.9/10AI resale manager. Photograph an item, AI writes the listing, publish a sale page, manage pickups.
Verbaterm
4.9/10Judged, citation-checked policy corpus over MCP. Keyless public reads; API key for AI tools.
Undertow
4.9/10Dated exit evidence, depth, tiers and gold cash scenarios. No executable quotes or trade authority.
Agent Index
4.9/10Measured uptime, price and payment evidence for 19,021 agent services. Reliability, not quality.
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.