Model Context Protocol moderate risk

Databricks

An MCP server enabling LLMs to interact with Databricks for SQL queries, job management, and workspace information, secured by API token.

Connections & Capabilities

Connects To

GitHubTwitter

Capabilities

readwriteexec

Quickstart

Install

npx @modelcontextprotocol/inspector python3 main.py

Exposed MCP Tools (4)

moderate

run_sql_query

Executes a SQL query against a Databricks SQL warehouse.

Potential for SQL injection and data modification if not properly sanitized.

safe

list_jobs

Lists all Databricks jobs in the workspace.

Read-only operation that retrieves a list of jobs.

safe

get_job_status

Retrieves the status of a specific Databricks job by ID.

Read-only operation that retrieves job status information.

safe

get_job_details

Retrieves detailed information about a specific Databricks job.

Read-only operation that retrieves job details.

Safety Assessment

This server provides useful Databricks interaction capabilities but relies heavily on the security of the Databricks API token. It's relatively safe for read-only operations, but the `run_sql_query` tool introduces a moderate risk depending on how user inputs are handled.

Uses API token for authentication, allowing for permission scoping.
No direct shell access or filesystem writes.
Clear separation of concerns with defined MCP tools.
Includes troubleshooting steps for connection issues.

Relies on user-managed API token security.
Potential for SQL injection if input sanitization is not implemented correctly in `run_sql_query`.
Lack of built-in rate limiting could lead to abuse.
`.env` file management poses a risk if not handled securely.