Agents & Machines
stopAgent
Stop Agent
Stop one of your running agent sessions: a graceful halt of an agent you started, for a runaway, duplicate, or no-longer-needed run.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "stop that agent", and it calls stopAgent.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"conversationId": "<conversationId>"
},
"name": "stopAgent"
}Arguments
conversationIdstringrequiredThe agent session to stop: the conversationId of a live session from listAgentSessions (each row carries it).forcebooleanoptionalForce-clear a STUCK session a graceful stop can't reach: one frozen in queued/starting because its daemon died mid-claim, jamming the machine's lane so every later session queues behind it and never starts. This skips the daemon entirely…
Returns
The registry does not declare a return shape.
Ask for it
The Cloud routes these requests to this verb.
- stop that agent
- halt the agent
- kill the run
- cancel that agent
- stop the runaway/duplicate agent
- clear the stuck session
- unjam the machine
Pair it with
The verbs that finish the job.
Questions
What does stopAgent do?
Stop one of your running agent sessions: a graceful halt of an agent you started, for a runaway, duplicate, or no-longer-needed run. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use stopAgent 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 "stop that agent", and it calls stopAgent.
Is stopAgent safe to let an AI call?
stopAgent changes your workspace. What an AI creates is Private until you share it.
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.