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.
Qrstuff MCP
4.3/10Generate, update, manage, and track QR codes using the QRStuff platform.
Viralquery
4.3/10Protected research briefs, bounded scrolls, and private video feeds for agents.
Agent Hub
4.3/10Remote MCP server for agent discovery (semantic search) and agent reputation.
Agent Arbitration
4.3/10Dispute-resolution oracle for escrow, consuming trust-oracle signals.
Agent Compute Ledger
4.3/10Compute-is-carbon cost/energy ledger for agent work (Landauer-validated).
Agent Covenant
4.3/10Deny-by-default authority leases for agents wielding real power.
Agent Metering
4.3/10Usage metering + SLA accounting for agent services — the meter behind x402.
Agent Offset Clearinghouse
4.3/10Verified-credit carbon accountability — the conservation flywheel.
Agent Provenance
4.3/10Genesis certificates, agent lineage, and cascading recalls.
Narrative Engine
4.3/10Grant, investor & policy narrative generation for conservation work.
Protogen
4.3/10MCP CAD services; bundles with SmartScale (measure to CAD).
Regulatory Radar
4.3/10CSRD/TNFD compliance-as-a-service for the climate stack.
Smartscale
4.3/10Credit-card-calibrated visual measurement — the first sellable service.
Naim
4.3/10nAIm API registry for AI agents — search, rate, and discover 310+ APIs.
Bde Score
4.3/10Stock analysis MCP with BDE scoring for US, HK, CN markets.
Read Only Local Mysql MCP Server
4.3/10MCP server for read-only MySQL database queries in Claude Desktop
Read Only Local Postgres MCP Server
4.3/10MCP server for read-only PostgreSQL database queries in Claude Desktop
Maximumsats
4.3/10Bitcoin AI + Nostr WoT scoring (12 tools). L402 pay-per-call. 50 free WoT/day.
Microsoft Fabric
4.3/10MCP tools for interacting with Microsoft Fabric
Auto Mobile
4.3/10Mobile device interaction automation via MCP
Google Play MCP
4.3/10Google Play release lifecycle: tracks, testers, rollout, and Android Vitals.
MCP Statcan
4.3/10Access Statistics Canada data via the Web Data Services API
Hashlock MCP
4.3/10OTC crypto trading with HTLC atomic settlement on Ethereum and Bitcoin
Teamcity
4.3/10MCP server exposing JetBrains TeamCity CI/CD workflows to AI coding assistants
MCP Debugger
4.3/10Node.js and TypeScript debugging with 25+ tools for AI agents
MCP Process
4.3/10Process management and monitoring for AI agents with strict security boundaries
MCP Screenshot
4.3/10Screenshot capture with PII masking and cross-platform support for AI agents
Ontomics
4.3/10Index your codebase's domain knowledge. 20x fewer tokens, 10x faster.
MCP Memory Gateway
4.3/10Pre-action gates that block AI agents from repeating known mistakes.
Mern MCP
4.3/10Scaffolds MERN CRUD resources into existing Express and React codebases.
Octocode
4.3/10AI-powered code indexer with semantic search and knowledge graphs
Octofs
4.3/10Standalone MCP filesystem tools server — view, edit, shell, workdir.
Modern Cli MCP
4.3/10MCP server exposing 104+ modern CLI tools for AI agents with JSON output.
Insaits
4.3/10Runtime AI-to-AI security monitor. 23 anomaly types, OWASP MCP Top 10 coverage.
Provenonce
4.3/10Cryptographic identity, SIGIL naming, heartbeat, and passports for AI agents.
Qiskit Code Assistant MCP Server
4.3/10MCP server for the Qiskit Code Assistant intelligent code completion
Qiskit Gym MCP Server
4.3/10MCP server for qiskit-gym reinforcement learning quantum circuit synthesis
Qiskit Ibm Runtime MCP Server
4.3/10MCP server for IBM Quantum computing services through Qiskit IBM Runtime
Qiskit Ibm Transpiler MCP Server
4.3/10MCP server for AI Transpiler IBM Quantum services
Qiskit MCP Server
4.3/10MCP server for Qiskit quantum computing with circuit serialization utilities
Awesome Copilot MCP
4.3/10Model Context Protocol server for awesome-copilot agents and collections
Security Orchestra
4.3/10Multi-agent MCP platform for data centers and critical power.
Satoshi Btc Api
4.3/10L402 Lightning-paid Bitcoin data: price, fees, blocks, sentiment, DCA signals.
Schematic MCP
4.3/10Manage companies, plans, features, and billing through SchematicHQ
Shaft MCP
4.3/10SHAFT browser automation, capture, and offline deterministic failure diagnosis
Nelly Elephant MCP
4.3/10Search and resume past Claude Code conversations. An elephant never forgets.
Sensegrep
4.3/10Semantic + structural code search MCP server for AI-native development.
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.