Search transcripts
Meetings whose transcripts match a phrase, with date and the matching passage.
MCP tool otter_read → search_transcripts
read
Searches the transcripts of every conversation you can open, including conversations shared with you, across all dates. Each result carries the conversation ID, the date and the passage that matched, so you can decide what to open with get_transcript. Results are ranked by match, not by date. A transcript holds what every participant said, so treat its content as theirs too.
Parameters
| Name | Type | Description |
|---|---|---|
| query string required | string | Words or a phrase to find. |
| limit integer | integer | Page size. Default: 20. |
| cursor string | string | Next page cursor from the previous call. |
tools/call
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "otter_read",
"arguments": {
"operation": "search_transcripts",
"arguments": {
"query": "query"
}
}
}
} Example response
{
"content": [
{
"type": "text",
"text": "{ ... same JSON as structuredContent ... }"
}
],
"structuredContent": {
"results": [
{
"conversation_id": "cv_7f3a91",
"title": "Pricing review with Acme",
"created_at": "2026-10-13T14:00:00Z",
"passage": "Sam Lee 12:41: We decided to go with the flat-rate option for the pilot."
}
],
"next_cursor": null
},
"isError": false
}