List connected data sources (id, name, type). Call this first to get data_source_id.

List tables in a data source. Use keyword to filter by name. Verify table names here before writing SQL.

Get column names and types for one or more tables (comma-separated). Verify columns before writing SQL.

Execute SQL against a data source and return results. Check schema with list_tables and get_table_columns first.

List saved queries in Redash.

Execute a saved query by ID and return results.

Get saved query details (SQL, visualizations, tags).

Save a new query to Redash.

Update a saved query's name, SQL, description, or tags.

Fork (duplicate) an existing query.

Archive (delete) a query. This action is irreversible.

List dashboards in Redash.

Get dashboard details including widgets and visualizations.

Create a new dashboard.

Add a visualization widget to a dashboard. Get visualization_id from get_query.

List alerts in Redash.

Get alert details (threshold, linked query, state).

Create a new alert. Triggers when a query result column crosses a threshold.

BIRD SQL-based intelligent query tool. Analyzes natural-language questions to (1) extract relevant schema, (2) match similar few-shot examples, (3) assess complexity, (4) request clarification for ambiguous questions. Call this tool before run_query. For a new data source, first inspect the schema with list_tables, then register keyword-to-table mappings via manage_keyword_map to significantly improve accuracy. Note: when ANTHROPIC_API_KEY is set, table-name lists (never query results or row data) may be sent to the Anthropic API as a fallback for table selection.

Manage few-shot examples (list/add/remove). Register domain-specific examples to improve SQL accuracy.

Submit feedback on generated SQL. Incorrect SQL is automatically classified and may be promoted to a few-shot example.

Manage SQL accuracy evaluation. Add/list test cases, run evaluations, and view results.

Manage keyword-to-table-name mappings. After inspecting the schema with list_tables, register domain-specific mappings to improve smart_query table-matching accuracy. e.g., {"revenue": ["payment"], "creator": ["creator"]}

View BIRD SQL configuration and status.