Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks
Cost Guard MCP is an MCP integration. Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks.
The published pypi package is cost-guard-mcp, version 0.3.2. Its declared MCP transport is stdio.
The package declares GOOGLE_APPLICATION_CREDENTIALS: BigQuery: path to a service-account key file (Application Default Credentials). Required to use the bigquery engine.; SNOWFLAKE_ACCOUNT: Snowflake: account identifier. Required to use the snowflake engine.; SNOWFLAKE_USER: Snowflake: username. Required to use the snowflake engine.; SNOWFLAKE_ROLE: Snowflake: role to assume. Required to use the snowflake engine; has no default and must never be ACCOUNTADMIN.; SNOWFLAKE_PRIVATE_KEY_PATH: Snowflake: path to an RSA private key file for key-pair auth (preferred over SNOWFLAKE_PASSWORD). Either this or SNOWFLAKE_PASSWORD is required to use the snowflake engine.; SNOWFLAKE_PRIVATE_KEY_PASSPHRASE: Snowflake: passphrase for an encrypted SNOWFLAKE_PRIVATE_KEY_PATH key file, if the key is encrypted.; SNOWFLAKE_PASSWORD: Snowflake: password (discouraged; prefer SNOWFLAKE_PRIVATE_KEY_PATH). Either this or SNOWFLAKE_PRIVATE_KEY_PATH is required to use the snowflake engine.; DATABRICKS_SERVER_HOSTNAME: Databricks: SQL warehouse server hostname (e.g. my-workspace.cloud.databricks.com, no scheme, no trailing slash). Required to use the databricks engine.; DATABRICKS_HTTP_PATH: Databricks: SQL warehouse HTTP path (from the warehouse's Connection Details tab, e.g. /sql/1.0/warehouses/ ). Required to use the databricks engine.; DATABRICKS_TOKEN: Databricks: personal access token (simplest auth option). Either this or DATABRICKS_CLIENT_ID + DATABRICKS_CLIENT_SECRET is required to use the databricks engine.; DATABRICKS_CLIENT_ID: Databricks: OAuth machine-to-machine service-principal client ID (preferred for automated use). Requires DATABRICKS_CLIENT_SECRET as well.; DATABRICKS_CLIENT_SECRET: Databricks: OAuth machine-to-machine service-principal client secret. Requires DATABRICKS_CLIENT_ID as well..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 0.3.2 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related databases MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| GOOGLE_APPLICATION_CREDENTIALS | BigQuery: path to a service-account key file (Application Default Credentials). Required to use the bigquery engine. | Optional |
| SNOWFLAKE_ACCOUNT | Snowflake: account identifier. Required to use the snowflake engine. | Optional |
| SNOWFLAKE_USER | Snowflake: username. Required to use the snowflake engine. | Optional |
| SNOWFLAKE_ROLE | Snowflake: role to assume. Required to use the snowflake engine; has no default and must never be ACCOUNTADMIN. | Optional |
| SNOWFLAKE_PRIVATE_KEY_PATH | Snowflake: path to an RSA private key file for key-pair auth (preferred over SNOWFLAKE_PASSWORD). Either this or SNOWFLAKE_PASSWORD is required to use the snowflake engine. | Optional |
| SNOWFLAKE_PRIVATE_KEY_PASSPHRASE | Snowflake: passphrase for an encrypted SNOWFLAKE_PRIVATE_KEY_PATH key file, if the key is encrypted. | Optional |
| SNOWFLAKE_PASSWORD | Snowflake: password (discouraged; prefer SNOWFLAKE_PRIVATE_KEY_PATH). Either this or SNOWFLAKE_PRIVATE_KEY_PATH is required to use the snowflake engine. | Optional |
| DATABRICKS_SERVER_HOSTNAME | Databricks: SQL warehouse server hostname (e.g. my-workspace.cloud.databricks.com, no scheme, no trailing slash). Required to use the databricks engine. | Optional |
| DATABRICKS_HTTP_PATH | Databricks: SQL warehouse HTTP path (from the warehouse's Connection Details tab, e.g. /sql/1.0/warehouses/ ). Required to use the databricks engine. | Optional |
| DATABRICKS_TOKEN | Databricks: personal access token (simplest auth option). Either this or DATABRICKS_CLIENT_ID + DATABRICKS_CLIENT_SECRET is required to use the databricks engine. | Optional |
| DATABRICKS_CLIENT_ID | Databricks: OAuth machine-to-machine service-principal client ID (preferred for automated use). Requires DATABRICKS_CLIENT_SECRET as well. | Optional |
| DATABRICKS_CLIENT_SECRET | Databricks: OAuth machine-to-machine service-principal client secret. Requires DATABRICKS_CLIENT_ID as well. | Optional |
Inspect PostgreSQL schemas and run read-only queries with the archived MCP reference server. Review its maintenance status before choosing it.
Connect the Notion MCP server to search workspace content and work with pages and databases through Notion’s hosted OAuth service.
Use the Supabase MCP server to inspect database schemas, query project data and retrieve docs through a project-scoped connection.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.