get_project_summary

Get high-level metrics for this project: total calls evaluated, average Compass Score, Compass-score distribution, agent-lift band distribution, top signals by frequency, predicted-CSAT average, and agent count. Use for executive summaries or to understand overall performance trends. Optionally filter by date range.

Parameters

Parameter	Type	Required	Default	Description
date_from	string	no	—	Start date (ISO format). Optional.
date_to	string	no	—	End date (ISO format). Optional.

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_project_summary",
        {
            "date_from": "2026-01-01",
            "date_to": "2026-01-01"
        },
    )
    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.

{
  "total_calls": 1284,
  "date_range": {"from": "2026-01-01", "to": "2026-05-12"},
  "agent_count": 14,
  "avg_compass_score": 3.42,
  "compass_sample_size": 1102,
  "avg_predicted_csat": 4.1,
  "csat_sample_size": 1102,
  "compass_score_distribution": [
    {"bucket": "1.0-2.0", "count": 87},
    {"bucket": "2.0-3.0", "count": 211},
    {"bucket": "3.0-4.0", "count": 504},
    {"bucket": "4.0-5.0", "count": 300}
  ],
  "lift_distribution": [
    {"band": "strong_positive", "count": 122},
    {"band": "positive", "count": 318},
    {"band": "neutral", "count": 410},
    {"band": "negative", "count": 174},
    {"band": "strong_negative", "count": 78}
  ],
  "top_signals": [
    {"signal_key": "empathy_acknowledged", "frequency": 612},
    {"signal_key": "next_steps_clear", "frequency": 588}
  ]
}

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.