List all available tools on the remote Databricks MCP server.
AI agents call list_databricks_tools to retrieve information from Databricks MCP Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query/enumeration operation with no side effects. It retrieves metadata about available tools from the Databricks server, which is a Read category action. The severity is low because listing available tools presents minimal risk—it does not access sensitive data, execute operations, or modify state.
From the tool's definition Tool name 'list_databricks_tools' and description 'List all available tools on the remote Databricks MCP server' indicate a read-only query operation that retrieves and enumerates available tools without modifying any state.
Attacks that exploit this kind of access
List all available tools on the remote Databricks MCP server. It is categorised as a Read tool in the Databricks MCP Proxy MCP Server, which means it retrieves data without modifying state.
Register the Databricks MCP Proxy MCP server in PolicyLayer and add a rule for list_databricks_tools: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Databricks MCP Proxy. Nothing to install.
list_databricks_tools is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_databricks_tools rule in your PolicyLayer 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.
Set action: deny in the PolicyLayer policy for list_databricks_tools. 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.
list_databricks_tools is provided by the Databricks MCP Proxy MCP server (smaheshwari-ux/databricks-mcp-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →