Categories › Knowledge & Everyday › Research, papers & reference data
Open agentic-web datasets: Agent Trust Index, MCP stats, incident timeline. Read-only, CC-BY-4.0.
Remote server: your requests and data go to majorlabs.co. Claude Code: claude mcp add --transport http major-labs https://majorlabs.co/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
get_trust_index — The weekly Agent Trust Index: one composite score (0-100) for how safe the agentic web is to transact on, fused from code-safety, identity, get_mcp_ecosystem_stats — Aggregate statistics from the Major Labs weekly sweep of the MCP server ecosystem: census size, activity, transport and language breakdowns,list_incidents — A dated, sourced record of frontier AI control incidents: containment escapes, unsanctioned live-system actions, evaluation incidents, and iget_agent_identity_tracker — Every announced framework, protocol, standard, and regulation for AI agent identity, delegation, and know-your-agent (KYA) verification, datget_threshold_watch — Dated, hashed snapshots of the frontier labs' published safety frameworks, with diffs when a framework changes. A change event means a lab eNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.