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.
Quickerspot MCP
4.7/10Servidor MCP do QuickerSpot para vinhetas, rádio indoor e sonorização comercial com IA.
Tmcra MCP Server
4.7/10Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.
Agent Action Gate
4.7/10Gate/Prove: deny unattended destructive agent tools. Instant Audit $499 on a2zsoc.com.
Komnet
4.7/10Lets AI coding agents coordinate asynchronously through a private git repository. No server.
Realagent MCP
4.7/10AI agent real-name identity: SM2 keypair, QR real-name link, SD-JWT VP generate/verify.
Thoughtproof MCP
4.7/10Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
Reality Next Door Walk
4.7/10Walk a cited post-extraction Seattle as an MCP world: go(), talk_to(), do(). Read-only, untracked.
Cost Of Work
4.7/10Cost of 13 back-office tasks per unit: person vs software, US, Greece, Ukraine. Sources cited.
Fairseal MCP Server
4.7/10Verifiable entropy, provably-fair games, and receipt verification for AI agents (FairSeal API).
Audiobookshelf MCP
4.7/10Browse your Audiobookshelf libraries and keep listening progress, bookmarks and playlists in sync
Linkwarden MCP
4.7/10MCP server for Linkwarden, the self-hosted bookmark manager with page preservation
Janus MCP
4.7/10Secure Kubernetes MCP server: scoped, redacted diagnostics and human-approved writes
Nutanix MCP
4.7/10Multitenant Streamable HTTP bridge over Nutanix's official v4 API MCP server (Prism Central).
MCP Samsara
4.7/10Samsara fleet management — vehicles, routes, drivers, HOS compliance. Unofficial, bring your token.
Kittyclaw
4.7/10Drive KittyClaw, a self-hosted agent-fleet kanban, from any MCP client (embedded /mcp endpoint).
Newrelic MCP
4.7/10Secure, self-hosted New Relic observability and administration tools for MCP clients
Iterabledata
4.7/10Streaming read, convert, and inspect 100+ formats. Install iterabledata[mcp] and run iterable-mcp.
Footballcharts MCP
4.7/10Tables, results, model probabilities and Monte Carlo projections for 90+ football leagues.
Handset
4.7/10A business phone system for AI agents: send texts, place calls, read transcripts, buy numbers.
Ssh MCP Server
4.7/10Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.
Rasterly MCP
4.7/10Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
Metaplex Agent
4.7/10Deploy AI agents on-chain on Solana with an EIP-8004 identity. Deploy fee funds $THREE buybacks.
Framingui
4.7/10FramingUI design-system tools for coding agents: validate screens, check wiring, browse the catalog.
Triz
4.7/10Deterministic, read-only TRIZ knowledge: parameters, principles, matrix, tool routing, effects.
Mailprotector MCP
4.7/10MCP server for Mailprotector — customers, domains, users, quarantine, allow/block rules for MSPs.
Uisandbox
4.7/10Test your design on the real thing: load a built web app, turn its knobs, verify 1:1, export.
Archstone
4.7/10Compile your own business capabilities from declarative YAML and serve them as MCP tools.
MCP Opa Authz
4.7/10Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.
Ar Studio
4.7/10Put 3D models in someone's real room: generate, arrange, and hand back one AR link.
Onchain Agent Wallets
4.7/10Give an AI agent a Solana spending allowance instead of your key. Chain-enforced cap, x402.
Pingpoint
4.7/10Live truck GPS tracking: create loads, read live position, ETA and trip stats, cancel a load.
Axcient MCP
4.7/10MCP server for Axcient x360Recover — BCDR clients, devices, jobs, vaults, and appliances.
Gagelink
4.7/10River level, streamflow, flood forecasts and basins from USGS, NOAA and SWOT, with units and datums
Chap
4.7/10Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
Commitlore
4.7/10Git-native decision memory for coding agents: only the decisions still in force for the edited path
Lazy Lions MCP
4.7/10Read the Lazy Lions NFT ecosystem: tokens, traits, rarity, holders, and the $LAZY economy.
Gigamail
4.7/10Your real mailbox and calendar for your agent (M365/IMAP); a human approves every send.
Test Intel
4.7/10Coverage analysis, untested function detection and complexity scoring for TS and JS.
Ennodia
4.7/10Local MCP server for AI team advice, multi-agent review, Compare, and traceable receipts
Verifiable Agent Audit Trail
4.7/10Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link.
Gov Data MCP
4.7/10US government open-data APIs as MCP tools: EPA, FEMA, USGS, NOAA, FDIC, HUD, CMS and more.
Mapsmith
4.7/10Deterministic GIS geoprocessing for AI agents, with verifiable provenance on every output
No Human
4.7/10File a task with your local no_human and check on it: task_add and task_status over stdio.
MCP Singapore
4.7/10Singapore public data, transport, rail, property, business, economy, weather, and analytics.
MCP Server
4.7/10Read-only MCP server for the open-banking.io PSD2 bank API — accounts, balances, transactions.
Orcalayer MCP
4.7/10Polymarket smart-money analytics: whale leaderboard, wallet P&L, market consensus, live alerts
Roast My Design System
4.7/10Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
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.