get_call_detail

Get full detail for a single call: metadata, transcript, Compass scores, agent lift, trust, signals, guidance, dimensions, and (optionally) raw conditions. Use session_id from search_calls or query_interactions results.

Parameters

Parameter	Type	Required	Default	Description
session_id	string	yes	—	The session_id of the call to retrieve.
include_transcript	boolean	no	True	Include full transcript. Default: true.
include_conditions	boolean	no	False	Include raw Compass conditions. Default: false.

Example call

from fastmcp import Client
from fastmcp.client.auth import BearerAuth

async with Client(
    "https://mcp.chordia.ai/mcp",
    auth=BearerAuth("YOUR_APPLICATION_KEY"),
) as client:
    result = await client.call_tool(
        "get_call_detail",
        {
            "session_id": "abc123"
        },
    )
    print(result.content[0].text)
# Plus any of the 2 optional params from the table above.

In Claude Desktop, Cursor, or any MCP-aware client the same call is issued by the LLM automatically once the server is configured — see integrations.

Result

Success responses are JSON of the shape below. Optional fields are omitted when the underlying data isn't present.

{
  "metadata": {
    "session_id": "a1b2c3d4",
    "agent_name": "Alpha Agent",
    "title": "Plan upgrade inquiry",
    "created_dt": "2026-05-10T14:22:00Z",
    "interaction_direction": "inbound",
    "interaction_driver": "sales",
    "language": "en",
    "customer_display_name": "Jane Doe",
    "company_name": "Acme Inc.",
    "location": "SF"
  },
  "scores_headline": {"compass_score": 4.1, "predicted_csat": 4.3},
  "talk_patterns": {
    "total_duration_s": 412, "hold_count": 0, "interruption_count": 1,
    "talk_time_ratio": 0.46, "avg_response_time_ms": 1180
  },
  "trust": {"level": "high", "score": 0.86, "reasons": ["consistent_tone"]},
  "scores": [
    {"key": "empathy", "display_name": "Empathy", "value": 4, "range": [1, 5]}
  ],
  "outcome_lift": {
    "lift": 0.22, "lift_band": "positive", "p_behavioral": 0.78,
    "p_context": 0.56, "is_scorable": true, "reliability": "high",
    "outcome_quality": "good", "present_signal_count": 9
  },
  "summary": {"text": "Customer asked about plan upgrade; agent..."},
  "signals": [
    {"signal_key": "empathy_acknowledged", "value": "present", "confidence": 0.92, "level": "high"}
  ],
  "guidance": [
    {"guide_key": "confirm_next_steps", "value": "followed", "guidance_kind": "behavior",
     "priority": "medium", "description": "Agent confirmed next steps explicitly."}
  ],
  "dimensions": [
    {"key": "intent_clarity", "value": "high", "confidence": 0.88}
  ],
  "transcript": [
    {"turn": 0, "role": "agent", "text": "Hi, this is Alpha..."}
  ]
}

Auth context

Every call receives the connection's project_id and access_scope automatically — the caller never passes them. See Authentication & RBAC for how scope narrows results.

Errors

All tools return JSON. Errors are wrapped in { "error": "..." }. The most common shapes are documented in Python integration → Error shape.