Loops
getLoopDetail
Get Loop Detail
Read ONE Loop in full: its prompt (the pinned recipe body), style preset, cadence, target, model, write policy and budgets, its consent record and whether consent is stale, plus its recent run…
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "what does this loop actually do", and it calls getLoopDetail.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"instanceId": "<instanceId>"
},
"name": "getLoopDetail"
}Arguments
instanceIdstringrequiredThe loop instance's id, from listLoops.
Returns
The registry does not declare a return shape.
Ask for it
The Cloud routes these requests to this verb.
- what does this loop actually do
- show me this loop's prompt
- what has my loop been reporting
- why did this loop fail
Pair it with
The verbs that finish the job.
Questions
What does getLoopDetail do?
Read ONE Loop in full: its prompt (the pinned recipe body), style preset, cadence, target, model, write policy and budgets, its consent record and whether consent is stale, plus its recent run… It is one of the tools The Cloud MCP server gives every connected AI.
How do I use getLoopDetail 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 "what does this loop actually do", and it calls getLoopDetail.
Is getLoopDetail safe to let an AI call?
getLoopDetail 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.