@qybbs/custom-bigquery-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ROW_LIMIT | No | Client-side row retrieval limit. | 1000 |
| GCP_PROJECT_ID | Yes | Your Google Cloud billing/execution project ID. | |
| ALLOWLIST_TABLES | Yes | Comma-separated list of BigQuery tables allowed for query execution, e.g. project.dataset.table1,dataset.table2. | |
| MAX_BYTES_BILLED | No | Hard cap on bytes billed per query. | 10737418240 |
| GCP_KEY_FILE_PATH | No | Path to a Google Cloud service account key file. Leave unset to use Application Default Credentials (ADC). |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_allowed_tablesB | List all BigQuery tables allowed for query execution. |
| describe_tableB | Get detailed schema, column descriptions, and partitioning information for an allowed BigQuery table. |
| estimate_query_costA | Estimate bytes scanned and projected cost in USD for a read-only SQL query without executing it. |
| execute_readonly_queryB | Execute a read-only BigQuery SQL query against allowed tables. |
| search_allowed_tablesA | Search allowed tables and their schemas by a keyword (e.g., 'transaction', 'customer'). Returns table description, partitioning columns, clustering columns, and field schemas in one call. |
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 5 tools
The five tools have largely distinct roles: listing, searching, describing, estimating, and executing. However, search_allowed_tables returns schema and partitioning details that overlap with describe_table, and list_allowed_tables overlaps with search_allowed_tables for table discovery. Descriptions clarify the differences, so confusion is limited.
All tool names follow a consistent snake_case verb_noun pattern (list_allowed_tables, describe_table, estimate_query_cost, execute_readonly_query, search_allowed_tables). Minor modifiers like 'allowed' and 'readonly' are used consistently and do not break the pattern.
Five tools are well-scoped for a read-only BigQuery querying server, covering discovery, schema inspection, cost estimation, and execution. No tool feels redundant or missing, making the count appropriate.
The surface covers the full read-only query lifecycle: discovering allowed tables (list/search), understanding their schemas (describe), estimating cost, and executing queries. No obvious gaps exist for the stated purpose, though bulk schema retrieval could be slightly more efficient.