ZBS Index What actually exists in applied AI, with the source next to it

Evaluation

Everything here was classified as evaluation by keyword match against the maintainer's own description, so treat the grouping as a starting point rather than a verdict.

The list is ordered by the most recent commit, not by stars. A popular project that stopped in 2024 is not a better answer than a smaller one shipped last week.

Listed, not yet verified by us (25)

Published to the registry, but we have not yet checked its repository. Treat the entry as the maintainer’s claim only.

Repository gone or archived (35)

The registry still lists these, but the linked repository returns 404 or the owner archived it. Shown so you do not spend time discovering that yourself.

  • com.benriscore/api — repository gone, v0.1.0
    Purpose-aware accessibility scoring for every coordinate in Japan.
  • DeepMap AI — repository gone, v2.0.0
    Multi-hazard geophysical risk scoring, prediction, weather, insurance, and climate tools
  • com.dintak/dintak-mcp-gateway — repository gone, v0.1.0
    Semantic job search, posting, and apply for Dintak, with resume-to-job match scoring.
  • MustertheForce MCP — repository gone, v1.0.0
    Salesforce-grounded retrieval, diagnoses, and a vetted-Force marketplace for MCP clients.
  • com.olane/copass-remote — repository gone, v0.1.0
    Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
  • com.olane/cosync-remote — repository gone, v0.1.0
    Knowledge graph ingestion, entity search, ontology analysis, and CoSync scoring.
  • Persimmon — repository gone, v0.1.1
    Brand-intelligence MCP: momentum scoring, signal evidence, and competitive context for agents.
  • PILLAR GTM OS — repository gone, v1.0.0
    AI-native GTM OS for B2B SaaS — account health, pipeline, renewals, territories, and benchmarks.
  • PromptOT — repository gone, v0.1.2
    Manage, version, and publish LLM prompts with blocks, variables, and evaluations.
  • com.rubrkit/rubrkit — repository gone, v1.0.0
    MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
  • Stratalize Crypto & DeFi — repository gone, v1.1.1
    Crypto and DeFi benchmarks: gas fees, chain TVL, stablecoin yields, options IV, and correlations.
  • Stratalize Finance — repository gone, v1.1.1
    Financial benchmarks: yield curve, FX, WACC, M&A multiples, PE returns, and bank capital ratios.
  • Stratalize Healthcare — repository gone, v1.1.1
    CMS benchmarks, travel nurse rates, pharmacy spend, billing risk, and payer intelligence.
  • Stratalize Intelligence — repository gone, v1.1.1
    Vendor benchmarks, H-1B wages, federal contracts, USPTO patent filings, and public financials.
  • Stratalize Real Estate — repository gone, v1.1.1
    Real estate benchmarks: cap rates, NCREIF returns, REIT, construction costs, and climate risk.
  • The Quiet Protocol Growth Offense MCP — repository gone, v1.0.0
    Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
  • EP AgentIAM — repository gone, v1.0.0
    AI agent execution safety via x402 micropayments: risk scoring, integrity, memory checks
  • io.github.andyscott88/agentsafe — repository gone, v1.0.1
    Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.
  • io.github.aruuhii2yo/maxion-mcp-gateway — repository gone, v16.4.0
    CPU telemetry & benchmarking, SHA-256 hashing, AES-256-GCM storage, AI video/image via Nova.
  • io.github.baronsengir007/openclaw-agent-tools — repository gone, v1.0.1
    Weather, code search, currency & Solana trust scoring as MCP tools. Free, no API key needed.
  • OpenClaw Trust Scorer — repository gone, v1.0.0
    Solana wallet trust scoring: tier, tx count, balance, liveness.
  • io.github.BlackhatShiftey/seam-runtime — repository gone, v1.3.1
    SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
  • Caplia — repository gone, v1.0.0
    MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
  • AgentIndex — Agentic Web Index — repository gone, v1.0.0
    Search 150k+ AI agents and MCP servers. Live liveness probes, behavioral benchmarks, x402 commerce.
  • io.github.collapseindex/ci1t-mcp — repository gone, v1.7.1
    CI-1T prediction stability engine. Detect ghosts, evaluate drift, monitor fleets. 20 tools.
  • Helium MCP Server - News, Markets & AI — repository gone, v1.0.1
    Real-time news with bias scoring, live market data, and AI-powered options pricing
  • io.github.CrazymakER23/convergealpha — repository gone, v1.0.0
    AI stock signal convergence � 13 sources, Bayesian scoring, verified outcomes.
  • io.github.CSOAI-ORG/meok-quantum-scoring-mcp — repository gone, v1.0.5
    MEOK AI Labs - quantum-scoring MCP server extracted from SOV3
  • VaultCrux Platform — repository gone, v0.1.0
    VaultCrux Platform — 60 tools: retrieval, proof, intel, economy, watch, org
  • io.github.dgtalquantumleap-ai/vigil-fraud-alert — repository gone, v1.0.1
    Proximity-based card fraud detection with AI risk scoring.
  • Homecastr MCP — repository gone, v1.14.0
    U.S. property forecasts, public benchmarks, and permit or environmental context through MCP.
  • Homecastr Remote MCP — repository gone, v1.14.0
    Remote MCP endpoint for U.S. home forecasts, public benchmark data, and permit or zoning readiness.
  • Worldcastr Remote MCP — repository gone, v1.14.0
    Built-environment forecasts, public benchmarks, and permit or zoning readiness through remote MCP.
  • io.github.digitamaz/clarvia — repository gone, v1.1.2
    AI agent tool discovery and scoring. Search 15,400+ MCP servers, APIs, and CLIs.
  • QACAT — repository gone, v1.0.0
    Translation QA: automated checks, AI evaluation, linguistic review, and visual in-context testing.

Page 3 of 7

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.