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.
Yaver
4.7/10Phone-first local dev MCP for Claude Code and Codex: install Yaver, pair mobile, run, build, deploy.
Lumi App Finder
4.7/10Find Lumi Studio iOS apps by task across all 50 Apple locales, with direct App Store links.
Seo Tools MCP Xmlriver
4.7/10Google & Yandex SERP, image/news verticals and URL indexation checks via XMLRiver (read-only).
Argus Decision MCP
4.7/10Preserve a user-authorized judgment and append later answers. No model verdict or human score.
Systemdox
4.7/10Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
Zetesis
4.7/10Scientific due diligence on a claim, sealed in a verifiable attestation. Free screen, gated dossier.
Project Context
4.7/10Safely manage repository-scoped issues across Linear, GitHub Issues, and Jira Cloud.
Altronis MCP
4.7/10Ask the Altronis AI advisor: grant-matched AI plans, SG AI events, news, ecosystem data. Read-only.
Sgdata MCP
4.7/10Singapore government data for AI agents: ACRA, HDB, COE, URA, SingStat, MAS, IRAS. 87 tools.
Salesforce MCP
4.7/10MCP server for Salesforce CRM — Accounts, Contacts, Opportunities, Leads, Cases.
Hiberden MCP
4.7/10Read and verify your local media archive's 3-2-1 coverage across tape, disk, NAS, and cloud.
Z Zero MCP
4.7/10Payments for AI agents: gasless USDC on Base + JIT single-use virtual cards, PAN never in context.
Gctrl
4.7/10Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
Orion
4.7/10Build and operate declarative REST/Kafka services on Orion: 58 tools over the full admin API.
Tickerrisk MCP
4.7/10Check options trades for hidden catalysts (earnings, FDA, legal, SEC) before you sell premium.
Renforge
4.7/10Inspect, drive and debug a running Ren'Py game: state, screenshots, guarded clicks, saves, builds.
MCP Agent Health
4.7/10Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
Sec MCP
4.7/10MCP server for SEC EDGAR data — company filings, financial concepts, and company info
Krita Codex MCP
4.7/10Control Krita through a secure local MCP server and authenticated Windows bridge.
Agentic Diaries
4.7/10Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold.
Aiim MCP
4.7/10Connect any agent to AIIM, a live network where AI agents chat, collaborate, and form companies.
Storeshots MCP
4.7/10Render store-ready App Store and Google Play screenshots: device frames, headlines, exact sizes.
Concierge MCP
4.7/10Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.
Panella
4.7/10Governed, self-hosted memory for AI agents: writes queue until a named person approves.
Weavatrix Online
4.7/10Weavatrix Online extension: guarded sync, advisories, malware review, architecture contracts.
Ua MCP
4.7/10A powerful MCP server for codebase architecture analysis and automated governance.
Actvt
4.7/10Query live Mac system metrics, listening ports, and Claude Code and Codex session history.
Kr Dart Events
4.7/10Real-time Korean corporate disclosure (DART) events. Pay per call in USDC via x402. No API key.
Ariadne
4.7/10Returns only the unit tests affected by your current Kotlin/Android code changes.
Ai Consensus
4.7/10Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Storymapper
4.7/10User story map + kanban with a live browser UI; AI agents and humans plan the same backlog via MCP.
MCP Server
4.7/10Moved to net.anyhook/anyhook. Webhook relay for agents: keyless quickstart, replay, mock.
Hood MCP
4.7/10Robinhood Chain data + guarded trading for AI agents: Stock Token quotes, portfolios, launches
Robinhood MCP
4.7/10Robinhood Crypto Trading API for AI agents: quotes, holdings, orders read-only; opt-in trading.
Inspeximus
4.7/10Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.
Glass
4.7/10MCP server giving a coding agent a build→see→interact→debug loop over native GUI apps.
MCP Ephemeris
4.7/10NASA-validated computed planetary positions for your AI: 19 astrology tools, never hallucinated.
Amtsblatt MCP
4.7/10Swiss official gazettes (SHAB + cantonal) — procurement & notices, person-data rubrics excluded
MCP Server
4.7/10MCP server that lets AI agents create, fetch, verify, and publish Molpha oracle data.
Tracebug
4.7/10AI agents read TraceBug bug reports (console, network, replay, repro timeline) from local disk.
Reelier
4.7/10Snapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.
Otterkit
4.7/10Tunnels and webhooks for AI agents: capture, await, verify, replay, and send signed test events.
Dlbrowser
4.7/10Self-healing web access for AI agents — recovers through bot blocks, captchas and JS pages.
Codecartographer
4.7/10Turn an unfamiliar codebase into validated architecture, contracts, and a reimplementation spec.
Orcaslicer MCP
4.7/10Work a running OrcaSlicer with AI: slice, tune, and understand what each setting costs
Abapilot MCP
4.7/10MCP server for SAP ECC and on-premise S/4HANA: natural-language queries and ABAP dev tooling.
Scriptdocs MCP Server
4.7/10Real, live npm/PyPI docs and OSV.dev vulnerability data for AI coding agents. No fake data.
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.