Cost Guard MCP Server

Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks

Local serverstdio

What is the Cost Guard MCP Server?

Cost Guard MCP is an MCP integration. Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks.

Packages and local setup

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..

Before connecting

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.

Project and source

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.

Configuration

VariableDescriptionRequired
GOOGLE_APPLICATION_CREDENTIALSBigQuery: path to a service-account key file (Application Default Credentials). Required to use the bigquery engine.Optional
SNOWFLAKE_ACCOUNTSnowflake: account identifier. Required to use the snowflake engine.Optional
SNOWFLAKE_USERSnowflake: username. Required to use the snowflake engine.Optional
SNOWFLAKE_ROLESnowflake: role to assume. Required to use the snowflake engine; has no default and must never be ACCOUNTADMIN.Optional
SNOWFLAKE_PRIVATE_KEY_PATHSnowflake: 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_PASSPHRASESnowflake: passphrase for an encrypted SNOWFLAKE_PRIVATE_KEY_PATH key file, if the key is encrypted.Optional
SNOWFLAKE_PASSWORDSnowflake: password (discouraged; prefer SNOWFLAKE_PRIVATE_KEY_PATH). Either this or SNOWFLAKE_PRIVATE_KEY_PATH is required to use the snowflake engine.Optional
DATABRICKS_SERVER_HOSTNAMEDatabricks: 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_PATHDatabricks: 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_TOKENDatabricks: 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_IDDatabricks: OAuth machine-to-machine service-principal client ID (preferred for automated use). Requires DATABRICKS_CLIENT_SECRET as well.Optional
DATABRICKS_CLIENT_SECRETDatabricks: OAuth machine-to-machine service-principal client secret. Requires DATABRICKS_CLIENT_ID as well.Optional