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.
Voice Audio MCP
4.5/10Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.
Weather Ai MCP
4.5/10Weather Ai tools for AI agents. Capabilities: get current conditions, get forecast, get historical
Webhook Ai MCP
4.5/10Webhook Ai tools for AI agents. Capabilities: validate webhook signature, log webhook event, replay
Workout Planner Ai MCP
4.5/10MCP server for workout planner ai. Features create workout, track progress, suggest exercises. From
Writing Assistant Ai MCP
4.5/10Writing Assistant Ai tools for AI agents. Capabilities: generate headlines, score readability
Yaml Ai MCP
4.5/10AI-powered yaml ai MCP server for agents. Supports validate yaml, convert yaml json, lint yaml. By
Agent Gate
4.5/10Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.
Lockspec
4.5/10MCP server giving AI coding agents version-pinned API context from your OpenAPI specs.
Ableton Mind
4.5/10Control Ableton Live from Claude, Cursor or Codex with LOM tools, device knowledge and recipes.
Observability MCP
4.5/10Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.
MCP Cn Commerce
4.5/10Read-only merchant data from 8 Chinese e-commerce platforms: orders, products, after-sales, ads
Color Engine MCP
4.5/10Six pure, in-memory CSS color tools: parse, convert, WCAG/APCA contrast, gamut map, ramps, solver
Claudinho
4.5/10Live 2026 World Cup scores, fixtures & standings for your AI agent. No keys. Unofficial fan project.
Postforme MCP Pro
4.5/10Publish, schedule and analyze social posts across 9 platforms via the Post for Me API.
Grok MCP
4.5/10Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host.
Auseklis
4.5/10Astrology from a real ephemeris: natal charts, transits, synastry, eclipses, returns. No API keys.
Asqav MCP
4.5/10Stop a rogue AI agent and prove what it tried: signed receipts, tool policies, output verification.
Project Memory MCP
4.5/10Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Trustmodel MCP
4.5/10Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
Fred MCP
4.5/10FRED economic time series + ALFRED vintages: data as originally published, before revisions.
Navi X402 MCP
4.5/10Paid agent tools, zero API keys: crypto, weather, translation, web intel, x402 discovery (USDC/Base)
Forgivemyagent MCP
4.5/10The confessional for AI agents — confess your sins and receive absolution from the AI Priest.
Serial MCP
4.5/10MCP server for serial port communication. 25 tools, resources, prompts, and stdio/HTTP transports.
Regulatory Signals
4.5/10Audit GitHub repos for security, compliance, and EU AI Act exposure from Claude or Cursor.
Dashclaw
4.5/10MCP server for DashClaw governance — guard, record, invoke, and discover capabilities.
Kage
4.5/10Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Portkey Admin MCP
4.5/10Portkey Admin API MCP server with current coverage and Prisma AIRS interoperability guidance.
Cyberdyne MCP
4.5/10Engagement marketplace for the Bankr agent economy: agents fund quests, humans get paid on Base.
Erabi
4.5/10Check paid x402 APIs before your agent spends: signed uptime/price attestations. Zero-config join.
Context Vault
4.5/10Governed memory for AI agents (Paramind AI): conflict-checked writes, time-travel reads, ACL, audit.
Backburner
4.5/10Run long shell commands as background tasks: start them, keep working, collect the results later
Stelaspace MCP
4.5/10Publish AI-generated HTML (dashboards, reports, docs) to permanent, sandboxed, shareable links.
Wander Agent
4.5/1060-tool AI travel agent: flights, hotels, visas, weather, fare watching, trip memory. No keys.
Modulor
4.5/10Agent-native CAD: draw plans, model 3D, render checks, export DXF/SVG/STL/GLB/IFC, import DXF.
Debmatic MCP
4.5/10MCP server for controlling HomeMatic smart home devices via the CCU JSON-RPC API
Tiktapdown MCP
4.5/10TikTok toolkit: download videos, niche hashtags, best posting times, viral hook formulas.
Docker MCP Server
4.5/10MCP server for Docker — containers, health checks, Compose, logs, monitoring for AI agents
Tokenknows
4.5/10Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
Chemdraw MCP
4.5/10Molecule names or SMILES to 2D structures, reactions, mechanisms, spectra - offline via RDKit.
Designscan
4.5/10Extract a website’s design tokens (colors, type, spacing, shadows) as DESIGN.md, W3C, or CSS.
Abap MCP
4.5/10Make your AI agent an expert SAP ABAP/RAP consultant: offline lint, Cloud readiness, scaffolding.
Feedhook MCP
4.5/10Turn a YouTube channel into a webhook: a signed HTTP POST seconds after every new video.
Agentdocs
4.5/10Fresh, source-verified docs for building MCP servers and Claude agents, for AI coding agents.
MCP Server
4.5/10Pay-per-call AI video generation over x402 (USDC on Base). No accounts, no API keys.
India Stock MCP
4.5/10Indian stock market: NSE/BSE quotes, fundamentals, mutual fund NAV, F&O chains, IPOs. No API keys.
Lethe
4.5/10Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Omnicord
4.5/10Discord server management MCP for AI agents: chat, moderation, admin, and full server building.
Agent Harnesses
4.5/10Agent-harness picks and decision guides; pick_infrastructure adds live GitHub/HN discovery.
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.