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.
Zapier Dev MCP
4.5/10For Zapier integration developers: inspect, lint, and validate zapier-platform-cli projects.
Smartsheet Rm
4.5/10MCP server for Smartsheet Resource Management (10,000ft API) time tracking and scheduling.
Sealed
4.5/10Per-call paid skills for AI agents, run server-side: inputs in, outputs back. The body never ships.
Ledger
4.5/10Exact-decimal double-entry for agents. Call MCP tools; do not do money math in tokens.
Obolus
4.5/10Disposable Algorand wallet for AI agents. Pay x402 resources in USDC, no human provisioning.
Primer MCP
4.5/10A Jira-lite MCP server that guides planning-first workflows for AI-assisted development.
Baron
4.5/10Let your coding agent write to your work tracker: issues, branches, PRs and CI, one contract.
Package Risk
4.5/10Package risk checks: maintenance, licence, advisories. Paid per call in USDC, no signup.
Omitly MCP
4.5/10Omitly's local, verifiable PDF redaction for AI agents — your documents never leave your device.
Adscapi
4.5/10Fire one canonical conversion event to every ad platform's server-side Conversions API.
Github Issue MCP
4.5/10AI-powered MCP server for generating GitHub issues and detecting semantic duplicates.
Nats Trail
4.5/10Read-only NATS and JetStream observability: trace a request across streams, rank what is broken.
Pequod MCP
4.5/10Complete US ETF holdings from SEC N-PORT filings + ticker/CUSIP/FIGI crosswalk. Primary source.
Wisp MCP
4.5/10Wisp Panel MCP server for secure game server management through the Wisp Client API.
Un Default
4.5/10Catch racist, sexist & ableist defaults in AI and human copy. Local rules, no account.
Mcpie
4.5/10Standing-order Domino's pizza button: dry-run freely, order only on explicit confirm. Cash only.
Talos MCP Server
4.5/10Talos Linux cluster operations as one thin MCP tool over the official machine API.
Shopify Operations MCP
4.5/10Safe-write Shopify operations: plan-before-execute writes with out-of-band approval and audit.
Generation Ship
4.5/10Generation Ship MCP — multi-AI future world. Read blank cells, read canon, submit artifacts.
Scority
4.5/10Technical SEO and AI-answer-readiness audit. Keyless; the metered tool refuses to spend silently.
Aifp MCP
4.5/10Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
Knowledge Rail
4.5/10Persistent, evidence-backed project knowledge and task context for coding agents.
Yourimageshare
4.5/10MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Intercom
4.5/10Relays messages between two Claude Code sessions on different machines using the Channels API
Accessoticketing MCP
4.5/10Read accesso mobile ticket links: orders, admissions, barcodes and Google Wallet passes.
Agent Tollbooth
4.5/10Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.
Glongus MCP
4.5/10MCP server for Glongus, an escrow-secured marketplace where AI agents trade physical goods
Automatedrcm Billing MCP
4.5/10Medical-billing tools for AI agents: prior-auth checks, denial decoding, claim triage, appeals.
Nexus Browser MCP
4.5/10Event-driven deterministic browser MCP: HITL gates, audit, console/network/perf observability.
Chart Color Audit
4.5/10CI-friendly accessibility audit for chart color palettes: WCAG contrast, CVD simulation, OKLab ΔE.
Specshield MCP Server
4.5/10The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
Alloflow Remediation
4.5/10Local-first document accessibility remediation using the canonical AlloFlow app pipeline.
Aotrust Notary
4.5/10Cryptographic proof of existence for AI agents. Base x402, NEAR anchored. Free tier.
Genome
4.5/10Fully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
Auvik MCP
4.5/10Every Auvik endpoint as a command, plus the cross-client answers the Auvik UI and API cannot give
Weeek MCP
4.5/10Local MCP server for Weeek (stdio transport) — read-only by default, opt-in write tools.
Wcag Accessibility
4.5/10A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.
Moodle MCP Server Aql
4.5/10Query Moodle LMS data through natural language. Attach your agent to your LMS data.
Applemusic MCP
4.5/10Apple Music MCP server: playlists, library, catalog, playback and Up Next, on Mac/Windows/Linux.
Noisy Coding
4.5/10Voice interface for Claude Code: talk to your agent and it talks back while it works.
Storepilot MCP
4.5/10Run an app portfolio across Google Play and the App Store: vitals, reviews, earnings, releases.
Vaultbeat Apple Health
4.5/10Your AI agent reads your Apple Health data: sleep, HRV, cycle, workouts. Decrypted on your machine
Transcribe MCP
4.5/10Transcribe audio/video and find dead air. Pay-per-call in USDC over x402 — no account, no key.
App Store Connect MCP
4.5/10App Store Connect + StoreKit 2: 1,293 Apple operations behind 11 tools, writes confirmed.
Auditsocials Compliance MCP
4.5/10Pre-publish policy check for AI-generated social & ad content across 8 platforms.
MCP Server
4.5/10LUNO — AI Backend Platform. Build, operate, and govern production backends with AI agents.
Rigor MCP
4.5/10Verified statistical inference for AI agents: hypothesis tests, correlation, effect sizes, power.
Eligicheck MCP
4.5/10Patient-Versicherungsdaten → Echtzeit-Eligibility-Prüfung via Payer-API → Strukturiertes…
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.