AI agents call describe_uc_catalog to retrieve information from MCP Databricks Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'describe' pattern and context of Databricks UC (Unity Catalog) operations indicate this retrieves catalog metadata/structure without modification. However, severity is medium rather than low because unrestricted catalog enumeration could expose sensitive data schemas, column names, and sensitive information about organizational data structure to an AI agent that misuses it.
From the tool's definition Tool name 'describe_uc_catalog' with 'describe' prefix suggests schema/metadata retrieval; sibling tools include 'describe_uc_schema' and 'describe_uc_table' which are clearly read-only, plus 'list_uc_catalogs' indicating catalog browsing operations.
Documented attack patterns abuse exactly the kind of access describe_uc_catalog gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Databricks Server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_uc_catalog:
{
"version": "1",
"default": "deny",
"tools": {
"describe_uc_catalog": {}
}
}describe_uc_catalog is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
describe_uc_catalog. It is categorised as a Read tool in the MCP Databricks Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Databricks Server MCP server in PolicyLayer and add a rule for describe_uc_catalog: 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 MCP Databricks Server. Nothing to install.
describe_uc_catalog 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 describe_uc_catalog 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 describe_uc_catalog. 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.
describe_uc_catalog is provided by the MCP Databricks Server MCP server (rafaelcartenet/mcp-databricks-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 MCP Databricks Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 MCP Databricks Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.