MCP Tool Reference Low Risk

list_tables

Lists all tables in a specified Databricks schema with optional filtering

Part of the Databricks MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

Read

WHEN AI AGENTS USE THIS TOOL

AI agents call list_tables to retrieve information from Databricks without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions — but you may still want rate limits to control API costs.

WHY ENFORCE A POLICY ON LIST_TABLES

Even though list_tables only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

databricks.yaml
tools:
  list_tables:
    rules:
      - action: allow

See the full Databricks policy for all 6 tools.

DETAILS

Tool Name

list_tables

Category

Read

Risk Level

Low

MORE DATABRICKS TOOLS

SIMILAR READ TOOLS ON OTHER SERVERS

RELATED READING

FREQUENTLY ASKED QUESTIONS

What does the list_tables tool do?

Lists all tables in a specified Databricks schema with optional filtering. It is categorised as a Read tool in the Databricks MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_tables?

Add a rule in your Intercept YAML policy under the tools section for list_tables. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Databricks MCP server.

What risk level is list_tables?

list_tables is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_tables?

Yes. Add a rate_limit block to the list_tables rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block list_tables completely?

Set action: deny in the Intercept policy for list_tables. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides list_tables?

list_tables is provided by the Databricks MCP server (). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

ENFORCE POLICIES ON DATABRICKS

Open source. One binary. Zero dependencies.