Agents & Machines
readAgentOutput
Read Agent Output
Read back what a dispatched agent session actually PRODUCED: its full transcript, final output, and tool-call log: by conversationId.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "read the agent's transcript", and it calls readAgentOutput.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"conversationId": "<conversationId>"
},
"name": "readAgentOutput"
}Arguments
conversationIdstringrequiredThe session to read: the conversationId returned by runAgent (or from listAgentSessions).fromSeqnumberoptionalResume cursor for paging a long run: pass the nextSeq from a prior call to continue after it. Omit (or 0) to read from the start; the user turns ride the first page only.
Returns
This is the readback complement to getAgentResult: where getAgentResult returns the OUTCOME (state, final text, PR), this returns the WORK: every user turn, every block of the agent's text, and…
Ask for it
The Cloud routes these requests to this verb.
- read the agent's transcript
- what did the native run do
- show the tool calls
- read back the agent output
- did it call any tools
Pair it with
The verbs that finish the job.
Questions
What does readAgentOutput do?
Read back what a dispatched agent session actually PRODUCED: its full transcript, final output, and tool-call log: by conversationId. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use readAgentOutput 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 "read the agent's transcript", and it calls readAgentOutput.
Is readAgentOutput safe to let an AI call?
readAgentOutput 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.