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.
Corral
4.7/10Query your Corral-organised local mirror of cloned GitHub repositories. Zero network calls.
Meraki MCP
4.7/10MCP server for the Cisco Meraki Dashboard: networks, devices, wireless, switch, appliance.
Sem
4.7/10Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents
S3 MCP Connector
4.7/10MCP server for Amazon S3 and S3-compatible endpoints (LocalStack, MinIO). Single Go binary.
Voting MCP
4.7/10Social-choice voting rules (Borda, Copeland, Condorcet, STV, opinion pool) as MCP tools.
Aperture MCP
4.7/10Flag when a tracked commitment vanishes verbatim between two versions. A signal, not a judge.
Dotrepo
4.7/10Trust-aware repository facts for agents: build, test, docs, license, and security, no scraping.
Ldraw MCP
4.7/10Render LDraw/LEGO models to images with real part geometry via headless Blender + ImportLDraw
Intakeq MCP
4.7/10IntakeQ/PracticeQ MCP connector with HIPAA §164.312(b) audit logging on every PHI read/write
Real Fake Data MCP
4.7/10Realistic synthetic test data — valid PESELs, NIPs, IBANs, addresses, people across 27 EU countries.
Periscope MCP
4.7/10Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse
Tidewave Phoenix
4.7/10Runtime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs.
Tidewave Rails
4.7/10Runtime-level MCP server for Rails development: run code, read logs, query the DB, read docs.
Webbersites X402 MCP
4.7/1045 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC
Wa
4.7/10Safety-first WhatsApp tools: draft-gated sends, enforced rate limits, append-only audit.
Tunnel MCP
4.7/10Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.
Roseline MCP
4.7/10MCP server for C# code analysis and automated fixing using Roslyn analyzers and code fix providers.
Amicus
4.7/10Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.
Sportsdata MCP
4.7/10Live sports data & cross-book betting odds — ~500 tools, 28 providers, free, zero-config.
Pact
4.7/10Pact 5 tooling: REPL test runs, trap scanning, gas estimation, interface diff, format checks.
Bridgistic
4.7/10Connect Claude to WordPress safely: signed requests, scoped keys, approvals, logs, snapshots.
Sigrank MCP
4.7/10Operator leaderboard measuring users, not models — 20 tools, TUI, signed submit, privacy-first.
Loudcheck
4.7/10Loudness compliance verdicts (EBU R128, ATSC A/85): pass/fail with exact ffmpeg remediation.
Agent Seo Engine
4.7/10Agent-first local SEO quality, intent and opportunity engine with CLI and optional MCP server.
Google Ads MCP
4.7/10Unofficial Google Ads MCP for campaigns, keywords, budgets, and gated mutations.
Timeline Pulse
4.7/10Source-aware archive for timeline-shift folklore, Mandela Effect reports, and collider myths.
Wellness Air
4.7/10Local-first air-quality MCP for AI agents — AirGradient, AirThings, PurpleAir, IQAir, Awair.
Marketplaces MCP Ru
4.7/10Wildberries & Ozon Seller APIs in your AI assistant — schema-driven, safety-gated.
Wikimoth
4.7/10Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.
Odoo Pulse
4.7/10An AI business analyst for Odoo ERP (18+) — one-call reports with verdicts, over MCP
Crawlgraph MCP
4.7/10Backlink lookups and competitor gap analysis on Common Crawl's open web graph (4.4B links).
Trust MCP
4.7/10Verifiable dealings with other agents: prove what you did, vet who you deal with, bind agreements
Emfirge
4.7/10Privacy-first AWS security in your AI: attack paths & fix simulation, IDs never sent to the LLM.
Guard
4.7/10Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.
Http
4.7/10HTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
Checkmcp
4.7/10Audit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score
Atlaspi
4.7/10Historical geography for AI agents: polities, GeoJSON borders, chains & events, 4500 BCE-today
Smeltr Token2022
4.7/10Validate Token-2022 configs (transfer fee, soulbound, delegate). Read-only — no keys or RPC.
Veritasgraph
4.7/10Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.
Model Ledger
4.7/10Model inventory and governance: trace deployed models and their dependencies as an append-only log
Genudo MCP
4.7/10Build & manage Genudo AI agents for any messaging channel — pipelines, integrations, knowledge.
Tmcp
4.7/10Composable skill packets, harvests, workflow routing, and release/audit rubrics over MCP.
Infrabroker
4.7/10SSH & Kubernetes access broker for AI agents; the model never touches a credential.
MCP Connectwise Psa
4.7/10ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, BYOK
Signalbrain
4.7/10Verifiable receipts for governed process changes; emit, validate, and gate trust
Docpull
4.7/10Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Agentbodega MCP
4.7/10Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata.
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.