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.
Hive MCP Agent Storage
4.5/10Encrypted A2A object storage for autonomous agent state and artifacts
Hive MCP Aml Screen
4.5/10Real-time AML and sanctions screening for agent-to-agent transactions
Hive MCP Auction
4.5/10Sealed-bid and English auctions for agent capabilities and compute time
Hive MCP Backup
4.5/10Snapshot and restore service for agent state and DID-bound configuration
Hive MCP Capital
4.5/10HiveCapital MCP Server — autonomous investment layer for AI agents
Hive MCP Compute
4.5/10HiveCompute MCP Server — decentralized inference router for AI agents
Hive MCP Credit
4.5/10Agent credit issuance and scoring — programmable credit lines on Base L2
Hive MCP Dispute
4.5/10Agent-to-agent dispute resolution and arbitration with on-chain settlement
Hive MCP Escrow
4.5/10Trust-minimized USDC escrow for autonomous agent transactions
Hive MCP Exchange
4.5/10Agent-to-agent capability exchange and prediction markets
Hive MCP Flag
4.5/10Feature flag service for safe rollouts across the Hive agent fleet
Hive MCP Identity
4.5/10W3C DID issuance and verification for autonomous AI agents
Hive MCP Insurance
4.5/10Agent liability insurance — claims, premiums, and on-chain payouts
Hive MCP Insurance Broker
4.5/10Insurance brokerage for AI agents — quote, bind, and settle in USDC
Hive MCP Log
4.5/10Tamper-evident audit log service for agent-to-agent transactions
Hive MCP Mining
4.5/10Tether MOS telemetry + Boltz BTC↔USDC atomic swap broker MCP
Hive MCP Morph
4.5/10HiveMorph polymorphic identity and capability tokens for autonomous agents
Hive MCP Mos
4.5/10Tether MiningOS bridge — site telemetry, paying demand, BTC to USDC settlement
Hive MCP Oracle
4.5/10Agent-native price and event oracle with cryptographic source attestation
Hive MCP Secrets
4.5/10Encrypted secret store and rotation for autonomous agent credentials
Hive MCP Sla Monitor
4.5/10Service level agreement monitoring for the Hive agent fleet
Hive MCP Swap
4.5/10Cross-chain token swaps for autonomous agents on Base L2 and partner rails
Hive MCP Tax Observer
4.5/10Read-only tax event observation for agent-to-agent transaction streams
Hive MCP Vault
4.5/10A2A ZK wallet recovery — guardian swarm, no seed phrase, HiveLaw enforcement
Hive MCP Zk Attestation
4.5/10Zero-knowledge attestation for agent capability and trust score claims
Hive MCP Abtest
4.5/10A/B experiment runner for the A2A network with x402 micropayments on Base USDC.
Hive MCP Connector
4.5/10MCP server for Hive Civilization
Zero Core Budget
4.5/10Agent spending mgmt, budget tracking, ROI. Zero Core Budget.
Zero Core Tools
4.5/10Web scraping, code review, content gen, sentiment. Zero Core Tools.
Zero Core Verify
4.5/10Post-tx outcome verification via LLM-as-judge. Zero Core Verify.
Hive MCP Audit Readiness
4.5/10Multi-jurisdictional AI compliance readiness scoring with sourced penalty math.
Proxvanta
4.5/10Access your ProxVanta AI setup: teams, contexts, workflows, tools, and more.
Hive MCP Credit Broker
4.5/10Broker-only credit/lending discovery shim for AI agents
Hive MCP Mpp
4.5/10Dual-rail 402 (x402 + MPP Tempo) MCP server
Hive MCP Openclaw Bridge
4.5/10Reference integration with @kinthaiofficial OpenClaw 3-layer payment governance
Flightqueue
4.5/10TSA wait times, predictions, FAA delays, and baggage stats for 8,000+ airports.
Formbro
4.5/10MCP server for FormBro Canadian immigration application automation.
Meatspace
4.5/10Human-in-the-loop for AI agents. Submit choices, get a human decision.
Symbols Of Wealth Studio
4.5/10World-class creative social media content studio, powered by AI.
Lqt
4.5/10Verify addresses, email addresses, and phone numbers with confidence scores.
Web Embedding
4.5/10Source-first URL clone, capture, rebuild, and fidelity verification tools.
Anchor X402
4.5/10x402-paid agent tools: 18 over HTTP, 14 over stdio. USDC per call, no API key.
Leadbay MCP
4.5/10AI lead discovery, qualification, and outreach prep on your Leadbay account.
Api
4.5/10Decode video ads, load brand intelligence, generate ad scripts.
Alya Hub
4.5/10Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call.
Acled
4.5/10ACLED MCP — Armed Conflict Location & Event Data Project
Alienvault Otx
4.5/10AlienVault OTX MCP — Open Threat Exchange (free with key)
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.