Agents & Machines
readSeatScoreboard
Read Seat Scoreboard
Score every model on every seat on every attached machine over a window, off the runs themselves: how many lanes each one was given, how those lanes ended (completed, versus stopped, dropped,…
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "which model is doing best", and it calls readSeatScoreboard.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {},
"name": "readSeatScoreboard"
}Arguments
windowstringoptionalHow far back to score, "24h" or "7d". Omit for the last 24 hours.
Returns
The registry does not declare a return shape.
Ask for it
The Cloud routes these requests to this verb.
- which model is doing best
- how is the codex seat performing
- seat scoreboard
- AI diagnostics
- which model should get more lanes
- what did each model cost me
Pair it with
The verbs that finish the job.
Questions
What does readSeatScoreboard do?
Score every model on every seat on every attached machine over a window, off the runs themselves: how many lanes each one was given, how those lanes ended (completed, versus stopped, dropped,… It is one of the tools The Cloud MCP server gives every connected AI.
How do I use readSeatScoreboard from Claude or ChatGPT?
Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "which model is doing best", and it calls readSeatScoreboard.
Is readSeatScoreboard safe to let an AI call?
readSeatScoreboard is read-only: it changes nothing.
Connect
One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.