Categories › AI & Agents › Thinking, planning & prompt tools
Measured agent costs, a one-page agent summary check, and an offline access map. No sign-in.
Remote server: your requests and data go to agentblueprint.ai. Claude Code: claude mcp add --transport http agent-blueprint https://agentblueprint.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_benchmark_jobs — Lists the ten everyday jobs in Agent Blueprint's measured agent cost benchmark (2 November 2026): what each job was, how big its input was, estimate_agent_cost — Estimates the tokens and dollar cost of an AI agent task from the measured benchmark job closest to it. For jobs where cost grows with how mcheck_agent_one_page — Checks the structure of a one-page agent summary written from Agent Blueprint's template (https://agentblueprint.ai/agent-one-page-template)render_agent_map — Turns an agent's own inventory of its connections into Agent Blueprint's one-page access map: a single offline HTML page showing what the agNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.