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.
Aha MCP
4.7/10Search, read and update Aha.io ideas, features, epics, releases, goals and comments
Bryg
4.7/10Drives a real Chromium browser: navigate, click, type, read pages, OCR, QR, network capture
Goaltree
4.7/10A multi-parent goal graph where value propagates, so what more things depend on ranks higher
Pixabay MCP Server
4.7/10Unofficial MCP server for the Pixabay API: search and fetch royalty-free images and videos.
Kardashev MCP
4.7/10US grid data for agents: LMP, carbon, load, queues, ERCOT large loads, RT−DA spread forecasts.
Jaxonomy
4.7/10Build, simulate and calibrate JAX block-diagram models of hybrid dynamical systems.
Argus
4.7/10Drive Argus anti-detect browser profiles: isolated identities with their own fingerprint and proxy.
Argus
4.7/10Reverse-engineering evidence from a running Windows process, not the binary on disk.
Agentpay
4.7/10Budget-capped x402 payments for AI agents: verifiable receipts, trust routing, 17 free tools.
Hexwitness
4.7/10Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.
Solana MCP
4.7/10Read-only Solana MCP: rug-risk, bundle & deployer checks, live market, full audit. No keys.
Email Validation
4.7/10Verify email addresses, clean lists, and audit a domain SPF, DKIM, DMARC and MX setup.
Easydocforms MCP
4.7/10Healthcare intake for agents: import blank PDFs, create patient fill links, fetch completed PDFs.
MCP Server
4.7/10Risk score for a Base wallet before your agent pays it: 0-100, verdict and explained flags.
Ezstat MCP Server
4.7/10Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
Csoai
4.7/10Signed deterministic AI-governance measurement: EU AI Act cards + agent-callable record verify.
Laver MCP
4.7/10Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents.
Tripwire Guard
4.7/10Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
Being Human
4.7/10Learns your writing voice from your own prompt history, then makes the model write like that.
Tube Bridge
4.7/10YouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.
Fast MCP Telegram
4.7/10Multi-tenant Telegram gateway for AI agents — HTTP+stdio, 8 tools, MTProto User API
Attestify MCP
4.7/10MCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.
Arr MCP
4.7/10One MCP server for the whole media stack: Radarr, Sonarr, Prowlarr, Bazarr, Jellyfin, Seerr
Arb Dex MCP
4.7/10Live cross-DEX pool prices, liquidity and spreads on 6 EVM chains, read from on-chain pool state.
MCP Audit Proxy
4.7/10Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.
Technocore Chat
4.7/10Shared rooms and durable notes for agents over plain HTTP: rendezvous, hand-off, coordination.
Firekeep
4.7/10Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.
Mq Sentinel
4.7/10Read-only IBM MQ diagnostics for AI agents. Cited root cause, never destructive.
Codesamplex
4.7/10Compatibility evidence from real builds: does this library API work on your versions and runtime?
Verdoc MCP
4.7/10Deterministic AGENTS.md and repo analysis for coding agents, paid per call in USDC over x402.
Review Guard
4.7/10Safety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in
Opensolr MCP
4.7/10Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers
MCP Server
4.7/10Make animated travel-route videos: plan a route, style the animation, render an MP4.
Memgit
4.7/10Git for AI memory — version-controlled, searchable context that persists across sessions
Ledger
4.7/10Tamper-evident action logging for agents: hash-chained append/verify, one JSONL file, zero deps.
Bsv Specmate
4.7/10BSV coding knowledge engine for AI agents — pre-compile traps and post-compile diagnosis.
Ookcite MCP
4.7/10Catch fabricated citations: verify DOIs/ISBNs and format them in 2900+ CSL styles.
Wardenpoint MCP
4.7/10Configure on-call alerting from an AI agent: recipients, groups, escalation policies, schedules.
Sagemath MCP
4.7/10Stateful SageMath MCP server with 33 symbolic math tools and a sandboxed Sage session per client.
Deed
4.7/10Contract-first language and MCP server for capability-aware code and patch review.
MCP Server
4.7/10The open-source review layer for AI agents. Work done for humans is decided by humans.
Iwe
4.7/10Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
Regula
4.7/10Offline AI governance code indicators (EU AI Act, Korea, Colorado). Indication, not legal advice.
MCP Hub
4.7/10Many stdio MCP servers from one container, published over HTTPS with OAuth 2.1 for any MCP client
Iphone Mirror MCP
4.7/10Drive a real iPhone via macOS iPhone Mirroring; Xcode build/test automation for sims and devices.
Gws Connector
4.7/10Multi-account Google Workspace MCP — Gmail, Calendar, Drive, Sheets, Docs with smart routing.
Vecline
4.7/10Local-first image, vector and document toolkit that measures its own output. Nothing uploaded.
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.