Agent Blueprint MCP
OfficialRegionGlobal
/About Agent Blueprint MCP
This MCP server exposes Agent Blueprint's tooling for understanding and documenting AI agents. It provides measured cost data from a benchmark of everyday agent jobs, a checker for one-page agent summaries written from Agent Blueprint's template, and a renderer that turns an agent's connection inventory into a single offline HTML access map.
AI-generated listing based on the project's public information. It may contain errors: check the original source.
/How to use Agent Blueprint MCP
Show me the ten benchmark jobs with their typical and worst-case token and dollar costs
Estimate the cost of an agent task that reads a 200-page document
Check whether my one-page agent summary follows the Agent Blueprint template
Render my agent's connection inventory as an offline access map
/Agent Blueprint MCP tools
What your assistant can call once connected.
| Tool | What it does |
|---|---|
| list_benchmark_jobs | Lists the ten everyday jobs in Agent Blueprint's measured agent cost benchmark, with input size and typical and worst-case tokens and dollar cost. |
| estimate_agent_cost | Estimates tokens and dollar cost of an AI agent task from the closest measured benchmark job, given the size of the real input. |
| check_agent_one_page | Checks the structure of a one-page agent summary written from Agent Blueprint's template, verifying all seven numbered sections are present and in order. |
| render_agent_map | Turns an agent's inventory of its connections into a one-page offline HTML access map showing what it can read and change, approvals, and riskiest powers. |
/Before you connect Agent Blueprint MCP
Do I need a key or an account?
No. It connects without a key.
Which assistants does it work with?
Claude, ChatGPT, Gemini, Grok
Which countries does it work in?
Any country.
