BigQuery Validator
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BQ_PROJECT | No | GCP project ID | |
| BQ_LOCATION | No | BigQuery location (e.g., US, EU, asia-northeast1) | |
| SAFE_PRICE_PER_TIB | No | Default price per TiB for cost estimation | 5.0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| bq_validate_sqlA | Validate BigQuery SQL syntax without executing the query |
| bq_dry_run_sqlB | Perform a dry-run of a BigQuery SQL query to get cost estimates and metadata |
| bq_extract_dependenciesC | Extract table and column dependencies from BigQuery SQL |
| bq_validate_query_syntaxC | Enhanced syntax validation with detailed error reporting |
| bq_list_datasetsB | List all datasets in the BigQuery project |
| bq_list_tablesA | List all tables in a BigQuery dataset with metadata |
| bq_describe_tableB | Get table schema, metadata, and statistics |
| bq_get_table_infoB | Get comprehensive table information including partitioning and clustering |
| bq_preview_tableB | Get a preview of table data without running a query job (cost-free) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Several tools have overlapping purposes: bq_validate_sql and bq_validate_query_syntax both validate syntax, while bq_describe_table and bq_get_table_info both return table metadata. Agents could easily confuse these and pick the wrong tool.
Naming is mostly consistent with a clear bq_ prefix and snake_case verb_noun pattern. The main inconsistency is validate_sql versus validate_query_syntax, which are different names for the same kind of operation.
Nine tools is a reasonable count for a BigQuery exploration and validation server, but at least two pairs are redundant. Trimming the duplicates would make the set tighter without losing any real capability.
The server covers dataset/table discovery, schemas, partitioning/clustering metadata, data previews, SQL syntax validation, dry-run cost estimation, and dependency extraction. Minor gaps exist, such as no way to list columns independently or execute queries, but these are outside the validator scope.