MCP Examples

The examples below show MCP tool inputs. Your client chooses the MCP tool and sends the displayed JSON object.

Discover an operation

Search by outcome:

bctrl_search_api

{
  "query": "create agent conversation"
}

Then inspect the exact operation:

bctrl_get_operation

{
  "operationId": "conversations.create"
}

Start an Agent conversation

Agents attach to an existing Runtime:

bctrl_conversations_create

{
  "body": {
    "runtimeId": "rt_AAAAAAAAAAAAAAAAAAAAAA",
    "title": "Collect the monthly report"
  }
}

Send another message to the ongoing conversation:

bctrl_conversations_messages_create

{
  "pathParams": {
    "conversationId": "conv_AAAAAAAAAAAAAAAAAAAAAA"
  },
  "body": {
    "text": "Open the report and export it as CSV"
  }
}

Call a BCTRL Tool synchronously

bctrl_tools_call is the MCP operation tool. stagehand.act is the BCTRL Tool being invoked:

bctrl_tools_call

{
  "pathParams": {
    "toolRef": "stagehand.act"
  },
  "headers": {
    "BCTRL-Runtime-Id": "rt_AAAAAAAAAAAAAAAAAAAAAA"
  },
  "body": {
    "instruction": "Click Continue"
  }
}

Create a durable ToolCall

Use durable execution for asynchronous work or capabilities that may require input:

bctrl_tools_calls_create

{
  "pathParams": {
    "toolRef": "captcha.solve"
  },
  "headers": {
    "BCTRL-Runtime-Id": "rt_AAAAAAAAAAAAAAAAAAAAAA"
  },
  "body": {
  }
}

Read the returned ToolCall:

bctrl_tool_calls_get

{
  "pathParams": {
    "toolCallId": "tc_AAAAAAAAAAAAAAAAAAAAAA"
  }
}

If its status is requires_input, inspect prompt and responseSchema, then reply through bctrl_tool_calls_respond.

Inspect one unified Run trace

Agent turns, BCTRL Tool calls, human input, and direct browser automation are correlated under the Run:

bctrl_runs_trace_list

{
  "pathParams": {
    "runId": "run_AAAAAAAAAAAAAAAAAAAAAA"
  }
}

Use bctrl_runs_events_list for the raw event record and bctrl_runs_stream for bounded live SSE collection.