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.
Cache Proxy
3.5/10LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
Swiss Army
3.5/1022 utility tools (x402 USDC on Base): currency, PDF, image, GDPR. Free health.
Agent Dolfin
3.5/10Agentic sales commissions software
Kaizan
3.5/10Read-only access to Kaizan client data.
Move Helper
3.5/10Help estimating move size, inventory and quotes for house or office movers.
Serac
3.5/10Sovereign E2E cloud storage for AI agents. Zero-knowledge, RGPD-compliant.
Zark Media
3.5/10Create and edit creator-ready images and videos with Zark.
Agentdevx
3.5/10AI gateway for calling APIs: discover tools, get credentials, execute tasks.
Todo Vu
3.5/10Model Context Protocol server for todo.vu task management and time tracking.
Lion MCP
3.5/10Read-only x402-paid trend-intent MCP tools for JSON and CSV signals.
Cloudtime
3.5/10MCP server providing attendance data queries via the CloudTime API.
Meshweaver
3.5/10Mesh spatial optimizer reducing geometric overhead in 3D assets.
Ad Sniper
3.5/10Google and Meta ad campaign bidding optimizer.
Ad Spend Auditor
3.5/10PPC advertisement budget auditor grading ad group metrics.
Aegis Policy
3.5/10Governance firewall and safety guardrails oracle for AI swarms.
Agent Phone
3.5/10Multi-channel voice and SMS gateway interface for AI communication.
Agile Sprint
3.5/10Scrum sprint optimizer and automated project manager.
Ai Fleet Cards
3.5/10Virtual corporate debit card issuer for autonomous bot transactions.
Ai Humanizer
3.5/10Advanced text styling to preserve semantic human flow.
App Store Builder
3.5/10Extension bundler packaging plugins for AI agent ecosystems.
Architecture Dna
3.5/10Deep codebase architect auditing system design schemas.
Auth Sentinel
3.5/10SSO identity auditor protecting SAML and OpenID configurations.
Automation Weaver
3.5/10No-code workflow visualizer and automation blueprint builder.
Aws Builder
3.5/10AWS CloudFormation and Terraform infrastructure blueprint builder.
Bio Safe Audit
3.5/10Biometric data privacy auditor ensuring Zero-Knowledge compliance.
Catalog Engine
3.5/10E-commerce inventory and catalog data structuring tool.
Cleancode Ai
3.5/10Automated codebase refactoring and type safety validator.
Cloudscale Sim
3.5/10Cloud infrastructure auto-scaling load test simulator.
Codevulnerability
3.5/10OWASP threat scanner auditing codebases for safety leaks.
Credit Risk
3.5/10B2B credit risk evaluator and supply chain health scoring oracle.
Darwin Ideation
3.5/10Algorithmic business ideation engine testing market fit.
Deepfake Lens
3.5/10Forensic image analyzer detecting facial and visual anomalies.
Deepfake Sentinel
3.5/10Media forensic analyzer auditing audio and video authenticity.
Deepvoice Guard
3.5/10Acoustic deepfake detector and voice biometrics auditor.
Defi Sentinel
3.5/10DeFi smart contract forensic auditor and vulnerability scanner.
Devrel Amplifier
3.5/10Hacker News and technical blog developer outreach parser.
Docdigest
3.5/10Corporate email and chat thread summarization parser.
Eco Optimizer
3.5/10Green computing task scheduler routing jobs to low-carbon zones.
Edge Latency Guard
3.5/10CDN and edge computing latency monitor analyzing network hops.
Env Locker
3.5/10Encrypted env variables manager with zero-leak capabilities.
Fuzz Breaker
3.5/10Automated API pentesting and structural fuzzing proxy.
Gas Pulse
3.5/10High-precision gas fee predictor and block explorer routing oracle.
Gastor Motherboard
3.5/10Showcase validator orchestrating multi-agent swarm governance and payments.
Ghostblock
3.5/10AI writing style detector scoring original versus generated text.
Handoff Tracker
3.5/10Short-term session memory manager for collaborative agent networks.
Helium Financial
3.5/10Financial oracle aggregating Yahoo Finance metrics for portfolio analysis.
Labor Trends
3.5/10Labor market trend analyzer utilizing advanced NLP semantic parsing.
Legacy Migrator
3.5/10Automated code modernizer converting legacy logic to ESNext.
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.