`query_user_activity`¶

Query user activity within your project for admin users. Analyze user behavior, page views, and activity patterns from audit logs.

Admin-only tool — requires Admin or SuperAdmin role.

Query types: - summary: Overview metrics (user count, total requests, avg daily activity, top 10 active users) - user_detail: Activity for a specific user (requires user_email) — pages, frequency, last active - active_users: List unique users with request counts and last activity - page_views: Most visited routes/pages with counts - recent_activity: Chronological list of recent activity events

Filtering behavior: - Automatically scoped to your current project (only activity with project_id) - Super admin users are excluded from all results - Use start_date/end_date to filter activity to specific periods

Parameters¶

Parameter	Type	Required	Default	Description
`query_type`	string (enum: summary, user_detail, active_users, page_views, recent_activity)	yes	—	Type of activity analysis to perform
`user_email`	string	no	—	Filter to specific user (required for user_detail query type)
`start_date`	string	no	—	ISO date string for start of time window.
`end_date`	string	no	—	ISO date string for end of time window.
`limit`	integer	no	`50`	Maximum number of results to return (1-100).

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(
        "query_user_activity",
        {
            "query_type": "summary"
        },
    )
    print(result.content[0].text)
# Plus any of the 4 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.

{
  "events": [
    {
      "user_id": "u_123",
      "user_name": "Casey",
      "action": "session_open",
      "session_id": "a1b2c3d4",
      "timestamp": "2026-05-10T14:21:00Z"
    }
  ],
  "count": 1
}

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.

query_user_activity¶