Agents & Machines
getAgentResult
Get Agent Result
Read the outcome of a dispatched agent session by its conversationId: the orchestrator readback that completes the dispatch→readback→synthesize loop.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "what did the agent produce", and it calls getAgentResult.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"conversationId": "<conversationId>"
},
"name": "getAgentResult"
}Arguments
conversationIdstringrequiredThe session to read: the conversationId returned by runAgent (or from listAgentSessions).
Returns
Returns: { state, isTerminal, workSummary, finalOutput?, pr?: { url, number?, title?, trackingState?, merged?, mergedAt?, mergeState? }, commits?, filesTouched?, turns?, pushedRefs?, durationMs?,…
Ask for it
The Cloud routes these requests to this verb.
- what did the agent produce
- get the agent result
- read the agent output
- did the PR open
- did it finish
Pair it with
The verbs that finish the job.
Questions
What does getAgentResult do?
Read the outcome of a dispatched agent session by its conversationId: the orchestrator readback that completes the dispatch→readback→synthesize loop. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use getAgentResult 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 did the agent produce", and it calls getAgentResult.
Is getAgentResult safe to let an AI call?
getAgentResult 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.