MCP Server Policy

DATABRICKS MCP POLICY

Enforce policies on every tool call to the Databricks MCP Server. 6 tools listed, categorised, and ready for rules.

5 read 1 write 6 tools total
databricks database

GET STARTED

Download this policy scaffold and add your rules. Intercept enforces them on every tool call before it reaches Databricks.

terminal

# Download policy scaffold

curl -o databricks.yaml https://raw.githubusercontent.com/policylayer/intercept/main/policies/databricks.yaml

# Run with Intercept

intercept --policy databricks.yaml -- npx -y @

Server documentation: https://docs.databricks.com/aws/en/generative-ai/mcp/

READ TOOLS

5

EXECUTE TOOLS

1

POLICY YAML

This scaffold lists every tool with empty rules. Add conditions — rate limits, argument validation, deny rules — then deploy with Intercept.

databricks.yaml 
version: "1"
description: "Policy for "
default: "allow"
tools:
    execute_sql:
        rules: []
    get_table:
        rules: []
    list_catalogs:
        rules: []
    list_schemas:
        rules: []
    list_tables:
        rules: []
    list_warehouses:
        rules: []

RELATED POLICIES

MongoDB 36 tools
database
Supabase 32 tools
database
Neon 29 tools
database
Couchbase 23 tools
database

FREQUENTLY ASKED QUESTIONS

What tools does the Databricks MCP server expose?

The Databricks MCP Server exposes 6 tools across 2 categories: Execute, Read. Each tool can be individually controlled with Intercept policies.

How do I enforce policies on Databricks?

Download the policy scaffold, add rules (rate limits, argument validation, deny rules), then run Intercept as a proxy in front of the Databricks MCP server. Every tool call is evaluated against your YAML policy before execution.

Is the Databricks policy free to use?

Yes. All Intercept policies are open source under the Apache 2.0 licence. Download, modify, and deploy without restrictions.

ENFORCE POLICIES ON DATABRICKS

Open source. One binary. Zero dependencies.

VIEW ON GITHUB Browse all policies →