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.
Planetary Agents
4.5/10Converse with planetary-agent personas, council feeds & culinary debates from alchm.kitchen
MCP Jp Doc Intel
4.5/10Japanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).
MCP S3
4.5/10Read-only S3/MinIO/R2 object storage for AI agents — list buckets/objects, metadata, fetch.
MCP Stripe
4.5/10Read-only Stripe for AI agents — customers, charges, subscriptions, invoices, balance.
Codmir
4.5/10AI-powered task execution, tickets, sprints, error debugging, and desktop control.
Agentsumo MCP
4.5/10MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.
Api Changelog
4.5/10SDK breaking-change tracker for AI agents — Anthropic/OpenAI/LangChain/MCP/Mistral.
Cve Cache
4.5/10Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).
Status Aggregator
4.5/10Cross-vendor SaaS status aggregator for AI agents (Anthropic/OpenAI/AWS/GH/Stripe/CF).
Java All Call Graph Server
4.5/10MCP server for Java call graph generation, static analysis, method chains & config management
Circle Agent Stack MCP
4.5/10Circle Agent Stack for AI agents: USDC wallets, spend policies, transfers, and x402 nanopayments.
Tokenscope
4.5/10Analyze Claude Code token cost & context attribution. Local, read-only MCP server.
Kalshi MCP Server
4.5/10MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.
Lithium Vault MCP
4.5/10Primary-source lithium & battery-metals mining data (AISC, reserves, filings) via x402.
Groupdocs Annotation MCP
4.5/10MCP server for GroupDocs.Annotation — add, list, update, remove document annotations via AI agents.
Iwantmymtg MCP
4.5/10Query Magic: The Gathering cards, sets, and prices and manage your I Want My MTG collection.
Edgar MCP
4.5/10SEC filings in your agent: issuers, Reg CF/D/A raises, XBRL financials, insider trades.
Presidio Hardened X402 MCP
4.5/10Pre-payment PII screener for x402 — catches emails, SSNs, names before agents sign.
Concord MCP
4.5/10Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.
Chain Signer
4.5/10Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.
Invovate MCP Server
4.5/10AI-agent invoice generator: PDF, JSON & UBL in 11 languages via the Invovate API.
Founden MCP
4.5/10Build your company over chat: website, app, and admin built in the cloud. One API key.
Steam MCP
4.5/10Read-only Steam: friends, games, achievements, sales, plus game recommendations and co-op nights.
Evite MCP
4.5/10Evite for Claude — list events, guest lists & RSVPs, RSVP, message guests, and create/edit events
Quick Html Share MCP
4.5/10Share AI-generated HTML from your coding agent. Unguessable URL + viewer analytics.
Logmcp
4.5/10MCP server — read-only log access for AI assistants, without giving AI shell access.
Leakferret
4.5/10Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
Qorami
4.5/10Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
MCP Sidecar
4.5/10Cross-platform MCP server for managing long-lived background processes from any MCP client
Recon Kit MCP
4.5/10Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.
Audit Ledger MCP
4.5/10Record AI decisions to a tamper-evident audit ledger from any MCP-compatible agent.
Starlog
4.5/10Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.
Veriswarm MCP
4.5/10VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol
Agent Memory
4.5/10Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
Trencher Agent
4.5/10First autonomous Solana trading agent on MCP. Live signals and consciousness feed.
Epanet MCP Server
4.5/10MCP server for EPANET water-distribution network simulation and scenario analysis.
Aml Ai MCP
4.5/106AMLD + UK MLR 2017 + FinCEN BSA AML/CFT compliance for AI-enabled transaction monitoring, sanct...
Basel Ai Overlay MCP
4.5/10Basel III + SR 11-7 + ECB TRIM AI/ML model risk management for banks deploying AI in credit, cap...
Chas Elite Prep MCP
4.5/10CHAS / SafeContractor / Constructionline pre-qualification preparation. Health & safety, environ...
Cobol Bridge MCP
4.5/10AI-assisted COBOL → modern stack bridge. Parse COBOL programs, map to Python/Java/Go, generate t...
Concrete Pump Cpa MCP
4.5/10CPA Concrete Pumping Group standards, pump operator certification, BS EN 12001 ground bearing ca...
Crane Hire Cpcs MCP
4.5/10CPCS / CISRS / NPORS card verification, BS 7121 lift plans, mobile crane / tower crane operator ...
Fda Samd MCP
4.5/10FDA AI/ML Software as a Medical Device Action Plan + 510(k) + PMA + De Novo pathways for US MedT...
Mdr Medical Device MCP
4.5/10EU MDR (Reg 2017/745) and IVDR (Reg 2017/746) compliance for medical device + IVD manufacturers...
Mica Crypto MCP
4.5/10Markets in Crypto-Assets (MiCA) Regulation (EU) 2023/1114 compliance for EU crypto-asset issuers...
Mifid Ii Ai MCP
4.5/10MiFID II Article 17 algorithmic trading + RTS 6 testing/risk controls + best execution AI compli...
Mitre Atlas MCP
4.5/10MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...
Nrswa Ai MCP
4.5/10UK street works compliance. Section 50 licences, S58 deferral, S74 overrun penalties, NRSWA accr...
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.