Screen for citation drift

Check how the citation landscape differs from a reference run. MCP tool: screen_drift. Operation: read. Uses the authorized connection; no project or content changes are made by this tool.

Parameters

Name	Type	Required	Default	Meaning and accepted values
`project_id`	string	Yes	`Required`	Project ID from list_projects. Select the project in the intended workspace and environment.
`run_id`	string	Yes	`Required`	Run ID from list_runs for this project. Use the exact returned value and check readiness before reading measurements.
`reference`	string or object or null	No	`null`	Choose the comparison run: previous_run, first_run, or specific_run. For specific_run, include run_id. The request’s run_id is the checkpoint.
`aggregation_level`	string	No	`'domain'`	domain requests source-domain results; url requests individual-page results. Keep the same reporting unit when comparing measurements.
`threshold`	number	No	`Omit for standard use`	Optional advanced drift-screen control. Omit for standard reporting; it is not the convergence SNR target.
`n_boot`	integer	No	`Omit for standard use`	Optional advanced analysis control. Omit for standard reporting; use the advertised runtime schema if an integration requires it.
`group_by`	string[] or null	No	`null`	Split results into rows by the requested dimensions. Check both filters_applied.group_by and each row’s group_by_values before labeling the groups.
`filters`	object[] or null	No	`null`	Select measured answers with objects containing dimension and values. Use labels from list_dimension_options; inspect returned warnings for filters that were not applied.

Example call

Replace ID placeholders and example selections with values from your account. This is the params object for MCP tools/call.

{
  "name": "screen_drift",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "reference": {
      "type": "previous_run"
    },
    "aggregation_level": "domain"
  }
}

Read the response

Returns landscape comparison data and the reference/checkpoint context. Inspect availability, warnings, and comparison fields rather than interpreting a single correlation as proof of change.

Fields to use

These selected fields explain the example and the result to preserve. Field presence depends on the response; this is not a complete response schema.

Field	Meaning and use
`data.reference_type`	Rule used to choose the reference run.
`data.rows[].is_drift_detected`	Returned comparison verdict; interpret together with sufficiency and warnings.
`data.rows[].is_sufficient`	Whether this comparison has sufficient evidence for the reported assessment.
`data.rows[].insufficient_reason`	Explanation when sufficient evidence is not available; null when no reason is supplied.
`data.rows[].n_domains_compared`	Number of source entries included in the comparison’s scope.

Response example

Selected fields from an observed IQRush Dev response. Lists are shortened and project/run IDs are placeholders. Omitted fields remain available in the actual response.

{
  "data_ready": true,
  "data": {
    "reference_type": "previous_run",
    "aggregation_level": "domain",
    "rows": [
      {
        "is_drift_detected": true,
        "is_sufficient": true,
        "insufficient_reason": null,
        "n_domains_compared": 175
      }
    ]
  }
}

Read the actual returned scope, counts, and interval levels before interpreting these fields.

Important behavior

Use for cross-run comparison. rank_correlation_resample_spread, when supplied, is a descriptive range and not a confidence interval on the point correlation. Leave advanced analysis controls at their defaults. Check tool and payload errors before using the result. Response handling explains estimates and empty results; errors and recovery covers invalid requests and temporary failures. HTTP equivalent: Screen for citation drift. HTTP parameters and defaults can differ.

Get started

Connect securely

Read measurements

Build dependable integrations

Build reports

Report recipes

Reference

Session and discovery

Visibility measurements

Sources and evidence

Changes and trends

Google data

Pages and report planning

HTTP operations

Screen for citation drift

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior

​Parameters

​Example call

​Read the response

​Fields to use

​Response example

​Important behavior

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior