### Answer To get the

call_id

and transcript when your agent uses an MCP tool, you have a couple of options: 1. Pass

call_id

as a dynamic variable to MCP You can use dynamic variables to pass the

call_id

into your MCP request via query parameters. [(1) ]() When configuring your MCP Node, you can add query parameters with dynamic variables to pass user inputs or call-specific data like the call ID. 2. Retrieve transcript after the call ends The

transcript

is available after the call ends. [(2) ]() [(3) ]() You can retrieve it by calling the Get Call API:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const callResponse = await client.call.retrieve('119c3f8e47135a29e65947eeb34cf12d') ;
console.log(callResponse) ;

[(3) ]() The response includes: -

call_id

- Unique id of the call -

transcript

- Transcription of the call (available after call ends) -

transcript_object

- Transcript as a list of utterances with timestamps -

transcript_with_tool_calls

- Transcript weaved with tool call invocation and results 3. Use webhooks You can also subscribe to the

call_analyzed

or

call_ended

webhook events to receive call data including the transcript once the call completes. Note that the transcript is not available mid-call—it becomes available after the call ends. [(2) ]() [(3) ]()

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

​ To learn more, see the sources I considered: [[1] Connect any AI Voice Agent to MCP with Retell AI MCP Node (Guide) | Retell AI](https://www.retellai.com/blog/connect-any-ai-voice-agent-to-mcp-with-retell-ai-mcp-node) [[2] Create Web Call](https://docs.retellai.com/api-references/create-web-call) [[3] Get Call](https://docs.retellai.com/api-references/get-call) ​

### Answer Yes, you can get the transcript using the `call_id`—but only after the call ends. [(1) ]() Use the Get Call API with the

call_id

to retrieve the transcript:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const callResponse = await client.call.retrieve('119c3f8e47135a29e65947eeb34cf12d') ;
console.log(callResponse) ;

The response includes the

transcript

field, which contains the transcription of the call. The key limitation is timing: the transcript is available after call ends, not during an active call. [(1) ]() [(2) ]() So if your MCP tool is being invoked mid-call and you need the transcript at that moment, it won't be available yet. You would need to retrieve it after the call completes using the

call_id

.

​ To learn more, see the sources I considered: [[1] Get Call](https://docs.retellai.com/api-references/get-call) [[2] Create Web Call](https://docs.retellai.com/api-references/create-web-call) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer To get the transcript mid-call, you need to use a Custom LLM with the LLM WebSocket. [(1) ]() When using the LLM WebSocket, Retell sends real-time transcript updates to your server via

update_only

events and

response_required

/

reminder_required

events. These events include a

transcript

field: -

transcript

- Complete live transcript collected in the call so far. Presented in the form of a list of utterances. Additionally, if you set

transcript_with_tool_calls

to

true

in your config event, you'll also receive: -

transcript_with_tool_calls

- Transcript of the call weaved with tool call invocation and results. It precisely captures when (at what utterance, which word) the tool was invoked and what was the result. To enable this, send a config event at connection open:

json
{
  "response_type": "config",
  "config": {
    "transcript_with_tool_calls": true
  }
}

**Summary**: If you're using the Retell LLM (single/multi-prompt) or Conversation Flow without a custom LLM WebSocket, mid-call transcript access is not available. You would need to implement a Custom LLM server that receives the WebSocket events to access the live transcript during the call.

​ To learn more, see the sources I considered: [[1] LLM WebSocket](https://docs.retellai.com/api-references/llm-websocket) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.