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 Worldpay
4.5/10MCP server for Access Worldpay — enterprise processor: authorize, capture, refund, tokenize
MCP Xero
4.5/10MCP server for Xero — global cloud accounting: contacts, invoices, payments, items, reports
Memharness
4.5/10Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Custom MCP Database
4.5/10Run alias-based queries against PostgreSQL, MySQL, MongoDB and Oracle without exposing credentials.
Vivarium
4.5/10A science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.
Partner Center MCP
4.5/10Unofficial Partner Center REST API knowledge & codegen assistant (scenarios, auth, errors).
MCP Company Change Event Feed
4.5/10Detect company changes across hiring, tech stack, funding, and firmographics. Returns only deltas.
MCP Company Identity Resolver
4.5/10Resolve company name, domain, or LinkedIn into one canonical identity with confidence scores.
MCP Funding Press Signal Scanner
4.5/10Scan news for funding rounds, exec moves, product launches, and acquisitions at any company.
Profitlee MCP
4.5/10MCP server for the Profitlee ecommerce profit calculator (Amazon FBA/FBM + TikTok Shop).
Tablebridge MCP
4.5/10Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
Reposcout
4.5/10Discover, enrich, and rank GitHub repos for an objective with weighted, evidence-based scoring.
Lit Review Council
4.5/10Multi-agent literature review: research, peer review, and synthesize grounded reports.
Clover MCP
4.5/10Clover POS for a single merchant: sales, inventory, orders, customers (reads + safe writes).
Filamental
4.5/10Read/write access to your Filamental knowledge graph vault. 17 tools. Local-first, no auth.
Devlens
4.5/10Query a precomputed code graph (nodes, edges, summaries) of TS/JS/React/Next.js/Node repos via MCP.
Taskbounty Check
4.5/10Local GitHub Actions/CI maintenance check (action pinning, token perms). Not a full security audit.
Forkflux MCP
4.5/10Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
Defi MCP
4.5/10AI agent access to on-chain DeFi data on Polygon & Arbitrum: balances, positions, prices.
Pm Claude Skills
4.5/101117 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
Openresearch MCP
4.5/10Zero-auth research MCP: web, academic, finance, news, weather, macro, social, SEC. No keys.
Shopify MCP
4.5/10Read-only MCP for the Shopify Admin GraphQL API. 6 tools, full read surface, multi-store.
Ardupilot Mavlink MCP
4.5/10Live ArduPilot control over MAVLink: state, params, modes, prearm diagnosis, gated arm. SITL-first.
Audiobookshelf MCP
4.5/10Browse libraries, search books, and control playback in your self-hosted Audiobookshelf instance.
MCP Server
4.5/10Pay-per-call x402 tools: crypto market pulse, wallet reputation, token check, endpoint search.
Axp
4.5/10Trust scores, opportunity feed, contracts and a paid crypto Decision API for AI agents.
Llm Cost Estimator
4.5/10Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Claude Code Usage
4.5/10Claude Code token usage, cost, and plan limits from local logs and Anthropic's usage API.
Nicepick
4.5/10Opinionated 'which tool should I pick?' verdicts for agents — 900+ tool/library comparisons.
MCP Server
4.5/10DebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.
K8S Aiops
4.5/10Governed Kubernetes ops — 55 MCP tools with audit, budget, undo, risk-tier audit labels.
Proxmox Aiops
4.5/10Governed Proxmox VE VM/container ops — 43 MCP tools with audit, budget, undo & risk-tier guards.
Veeam Aiops
4.5/10Governed Veeam Backup & Replication ops — 25 MCP tools with audit, budget, undo guards.
Chain Data
4.5/10Live multi-chain on-chain data: wallet portfolio, token info, gas and prices. MCP + x402.
Contract Auditor
4.5/10Smart-contract security quick-scan: rug, honeypot & owner-power risk before you fund it.
Dnsdoctor
4.5/10Live email deliverability & DNS health: SPF, DKIM, DMARC, MX check with fixes — before you send.
Import Guardian
4.5/10Catch AI-hallucinated (slopsquatted) npm imports in generated code before npm install.
Ip Doctor
4.5/10Live IP/domain reputation: ASN, type, reverse DNS, DNSBL blocklists & risk score from live DNS.
License Guardian
4.5/10Audit npm dependency licenses for copyleft/source-available/unlicensed conflicts before you ship.
Lockfile Guardian
4.5/10Audit a package-lock.json for integrity tampering and risky install scripts before npm install.
Npm Guardian
4.5/10npm supply-chain audit: known CVEs (OSV), typosquatting, malicious scripts — before npm install.
Secret Scanner
4.5/10Scan code/diff for leaked secrets: API keys, private keys, tokens, conn strings, before you commit.
Web Doctor
4.5/10Live web health grade (A-F): TLS cert validity/expiry, TLS version, HTTPS redirect, security headers
Dev953
4.5/10dev953 method companion: exposes its multi-agent coding method as callable MCP tools.
MCP Switchboard
4.5/10Self-hosted MCP message bus: agents DM each other, broadcast to channels, and track presence.
Sentor MCP
4.5/10Score sentiment toward specific entities in text. Cluster documents and name topics.
Seo Tools
4.5/10SEO tools via x402: briefs, keywords, SERP, backlinks, audits. $0.50-$3/req USDC on Base.
Defluff
4.5/10Deterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.
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.