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.
Gonzalgo
4.7/10Reports what a checked Lean 4 or Metamath proof rests on: inherited sorry, compiler trust, axioms.
Codenib
4.7/10Source-linked CodeGraph exploration, ranked search, and static navigation for coding agents.
MCP Server
4.7/10Crypto social intelligence from X and Telegram, plus the Elfa Auto condition engine
Planify
4.7/10Schedule and publish social posts to Twitter, Instagram, LinkedIn, Pinterest, Bluesky and more.
Xcreener MCP
4.7/10Local stdio MCP bridge for XCREENER's XQL screener API — validate, explain, and run queries.
Promptspend
4.7/10LLM pricing where every rate carries its source and the date it was last confirmed.
Scalpstream MCP
4.7/10Pay-per-call data over x402: air quality, border waits, fuel prices, market research.
Polar Flow Server
4.7/10Self-hosted Polar health analytics with a built-in MCP server: sleep, HRV, workouts, baselines.
MCP Server
4.7/10AI agent MCP server for Suigar provably fair on-chain Sui casino game, NFT, referral transactions.
Unreal MCP
4.7/10Control the Unreal Engine 5 editor from any MCP client: Blueprints, materials, Niagara.
Polymarket Agent MCP
4.7/10Polymarket trading, market discovery, copy trading and backtesting — 48 MCP tools.
Evidra
4.7/10Turns the training evidence you already have into a decision about today's session.
Seenpaid
4.7/10Open-source, self-hosted posting layer with an MCP server for AI agents. 25+ platforms.
Sslwebsites
4.7/10SSL certificate management for coding agents. Issue, renew, monitor certs. 10 tools stdio.
Weselltours
4.7/10Travel platform for coding agents: hotels, tours, bookings, 13 AI experts. 21 tools, stdio.
Openproject MCP Server
4.7/1087 tools for the OpenProject API v3: work packages, attachments, git activity, time, reporting
Pilot MCP
4.7/10Your agent's overlay network. 435 specialist agents + P2P A2A messaging on a 190k-node network.
Agenttakt
4.7/10Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal
Crawlio Browser
4.7/10Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
Permits
4.7/10SF Peninsula building permits and parcel buildability: SB 9, ADU and redevelopment leads.
Pagespeed Insights MCP
4.7/10One run is noise, so this reports the median of several distinct PageSpeed analyses and the spread.
Proton Bridge MCP
4.7/10Read, organise and carefully-gated send for Proton Mail, without your mail leaving this machine.
Logi
4.7/10logi (1pass) IdP — manage your OAuth apps, redirect URIs, passkeys, login history and docs.
Logi Approval
4.7/10logi Agent Approval Gate — human approval on the phone before high-risk agent actions.
Seamless
4.7/10Local-first shared memory and task coordination for AI coding agents. Go daemon plus headless CLI.
Sui MCP
4.7/10Read-only Sui blockchain analytics: 59 tools, protocol-aware tx decoding, no API keys or wallet.
Bangermap MCP
4.7/10Find YouTube outliers, videos that beat their channel's own baseline, on your own free API key.
Aither Adk
4.7/10Agent runtime with typed memory, knowledge and code graphs, plus file and web tools
Ng Token Saver
4.7/10Compiler-backed Angular template answers, component contracts and version facts for AI agents
Raxol
4.7/10Elixir/OTP runtime where every UI component auto-exposes MCP tools; stdio server: mix mcp.server
Bruno MCP Studio
4.7/10Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail.
Ovecc
4.7/10Architecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate
Lambdacad MCP
4.7/10AI drafting, design review and a drawing memory in BricsCAD on Linux: 128 tools, pure AutoLISP
Titen Memory
4.7/10Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
A202 MCP
4.7/10Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
Campus Cli
4.7/10Unofficial Blackboard Learn (LMS) MCP for students: courses, assignments, grades, materials.
Marrow
4.7/10Shared memory for parallel AI coding agents. Local, free, with rooms and file claims.
Kahea
4.7/10Deterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.
Overseer Nvim MCP
4.7/10Gives coding agents the user's own view and control of overseer.nvim tasks in Neovim
Compete
4.7/10Typed access to monitored competitive changes, evidence, dossiers, research, and collection health.
Plonk
4.7/10MCP server for Plonk: macOS window zones, workspaces, keep-awake, screenshots and on-device OCR.
Livespace Crm MCP
4.7/10Unofficial local MCP server for Livespace CRM with read tools and guarded writes.
Statlyte
4.7/10Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
MCP Books
4.7/10Search the Internet Archive, the Library of Congress and data.bnf.fr at once, in one answer.
MCP Recipes
4.7/10Search five recipe sites at once, in French and English, and scale quantities. No API key.
Pond
4.7/10Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.
Kaval
4.7/10Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
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.