List Calls

Read only Returns compact call log ROWS for the organization (status, direction, numbers, duration, cost, timestamps, agent, sentiment, a short summary, and has_transcript/has_recording flags), filterable by agent, status, sentiment and date range. Use it to find calls and to count them. It is NOT the source of truth for what happened on a call: sentiment and summary are written by post-call analysis after the call ends, so they are “unknown” or null on any call that has not been analysed yet. Every result carries an analysis_coverage block saying how many of the returned calls have been analysed: read it before drawing any conclusion about outcomes, and never report unanalysed rows as an absence of performance data. For what was actually said or concluded on one call, use get_call_details. For a single known call by ID, use get_call.

Parameters

Name	Type	Required	Description
`agent_id`	`string`	No	Filter by agent ID, e.g. agent_abc123. Comma-separate multiple IDs.
`status`	`string`	No	Filter by call status. One of: initiated, received, sent, did_not_pick, busy, failed, no_answer, completed, created, cancelled
`sentiment`	`string`	No	Filter by post-call-analysis sentiment. One of: positive, neutral, negative, unknown. Written by post-call analysis after the call ends, not by the call itself, so any call that has not been analysed is “unknown”. Filtering on “positive” therefore also excludes every call that simply has not been analysed yet.
`start_date`	`string`	No	ISO 8601 date — only calls on/after this date
`end_date`	`string`	No	ISO 8601 date — only calls on/before this date
`end_reason`	`string`	No	Filter by hang-up reason
`page`	`string`	No	Page number, default 1
`limit`	`string`	No	Results per page, default 10, max 50

Complete input schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Filter by agent ID, e.g. agent_abc123. Comma-separate multiple IDs."
    },
    "status": {
      "type": "string",
      "description": "Filter by call status. One of: initiated, received, sent, did_not_pick, busy, failed, no_answer, completed, created, cancelled"
    },
    "sentiment": {
      "type": "string",
      "description": "Filter by post-call-analysis sentiment. One of: positive, neutral, negative, unknown. Written by post-call analysis after the call ends, not by the call itself, so any call that has not been analysed is \"unknown\". Filtering on \"positive\" therefore also excludes every call that simply has not been analysed yet."
    },
    "start_date": {
      "type": "string",
      "description": "ISO 8601 date — only calls on/after this date"
    },
    "end_date": {
      "type": "string",
      "description": "ISO 8601 date — only calls on/before this date"
    },
    "end_reason": {
      "type": "string",
      "description": "Filter by hang-up reason"
    },
    "page": {
      "type": "string",
      "description": "Page number, default 1"
    },
    "limit": {
      "type": "string",
      "description": "Results per page, default 10, max 50"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Registered output schema

{
  "type": "object",
  "properties": {
    "calls": {
      "type": "array",
      "description": "Call log rows matching the filters — each a call record (status, direction, duration, cost, timestamps) with prefixed ids"
    },
    "analysis_coverage": {
      "type": "object",
      "properties": {
        "returned": {
          "type": "number",
          "description": "How many call rows were returned"
        },
        "analysed": {
          "type": "number",
          "description": "How many returned rows have post-call analysis (a summary or a non-unknown sentiment)"
        },
        "unanalysed": {
          "type": "number",
          "description": "How many returned rows have not been analysed yet"
        },
        "with_transcript": {
          "type": "number",
          "description": "How many returned rows have a readable transcript"
        },
        "meaning": {
          "type": "string",
          "description": "How to interpret these counts before drawing conclusions about outcomes"
        }
      },
      "required": [
        "returned",
        "analysed",
        "unanalysed",
        "with_transcript",
        "meaning"
      ],
      "additionalProperties": false,
      "description": "Post-call-analysis coverage for the returned rows"
    }
  },
  "required": [
    "calls",
    "analysis_coverage"
  ],
  "additionalProperties": true,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Before you call

Connect and initialize the MCP client with OAuth or an API key for the intended workspace.
This tool has no required arguments.

Example MCP request

Send tools/call after your client completes MCP initialization. Replace placeholder values with IDs and inputs from your workspace. For object and array parameters, follow the nested requirements in the parameter description instead of treating an empty value as complete.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "list_calls",
    "arguments": {}
  }
}

Successful results include structuredContent and a text content block containing the same JSON. Check isError first, then read structuredContent or parse content[0].text. See MCP responses and errors for the full envelope and failure behavior.

Verify the result

Confirm the response is not marked isError, parse content[0].text as JSON, and verify that returned IDs and workspace data match the request.

Retry safety

This tool does not change workspace data. Retrying after a transient transport failure is safe.

Get Call: get_call
Get Call Details: get_call_details

Start Here

Tool Reference

Parameters

Complete input schema

Registered output schema

Before you call

Example MCP request

Verify the result

Retry safety

​Parameters

​Complete input schema

​Registered output schema

​Before you call

​Example MCP request

​Verify the result

​Retry safety

​Related MCP tools

​Related guides

Parameters

Complete input schema

Registered output schema

Before you call

Example MCP request

Verify the result

Retry safety

Related MCP tools

Related guides