BigQuery MCP Server
by pvoo
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GCP_PROJECT_ID | Yes | Google Cloud project ID | |
| BIGQUERY_LOCATION | Yes | BigQuery location (e.g., US, EU) | |
| BIGQUERY_SAMPLE_ROWS | No | Sample data rows returned in get_table (default: 3) | 3 |
| BIGQUERY_DISTANCE_TYPE | No | Distance metric for vector search: COSINE, EUCLIDEAN, DOT_PRODUCT (default: COSINE) | COSINE |
| BIGQUERY_EMBEDDING_MODEL | No | Full path to embedding model (project.dataset.model) for vector search | |
| BIGQUERY_ALLOWED_DATASETS | No | Comma-separated list of datasets to restrict to (default: all datasets) | |
| BIGQUERY_EMBEDDING_TABLES | No | Tables with embedding columns for vector search (comma-separated) | |
| BIGQUERY_LIST_MAX_RESULTS | No | Max results for basic list operations (default: 500) | 500 |
| BIGQUERY_MAX_BYTES_BILLED | No | Max bytes billed per query job (default: 109951162777) | 109951162777 |
| BIGQUERY_SAMPLE_ROWS_FOR_STATS | No | Rows sampled for column fill rate calculations (default: 500) | 500 |
| BIGQUERY_VECTOR_SEARCH_ENABLED | No | Enable or disable vector search tools (default: true) | true |
| GOOGLE_APPLICATION_CREDENTIALS | No | Path to service account key file (default: Application Default Credentials) | |
| BIGQUERY_EMBEDDING_COLUMN_CONTAINS | No | Pattern for finding embedding columns (default: embedding) | embedding |
| BIGQUERY_LIST_MAX_RESULTS_DETAILED | No | Max results for detailed list operations (default: 25) | 25 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pvoo/bigquery-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server