AI agents call find-tables-by-name to retrieve information from Databricks Unity Catalog MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for tables by name in Databricks Unity Catalog, retrieving metadata without modification. It is a read-only query operation consistent with the other data discovery tools on this server. No data is created, modified, deleted, or executed—only queried.
From the tool's definition Tool name 'find-tables-by-name' and context of sibling tools (get-catalogs, get-schemas-in-catalogs, get-tables-details, get-tables-in-catalogs-schemas) all being retrieval/metadata operations.
Documented attack patterns abuse exactly the kind of access find-tables-by-name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Databricks Unity Catalog MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find-tables-by-name:
{
"version": "1",
"default": "deny",
"tools": {
"find-tables-by-name": {}
}
} find-tables-by-name 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.
find-tables-by-name. It is categorised as a Read tool in the Databricks Unity Catalog MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Databricks Unity Catalog MCP Server MCP server in PolicyLayer and add a rule for find-tables-by-name: 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 Unity Catalog MCP Server. Nothing to install.
find-tables-by-name 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 find-tables-by-name 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 find-tables-by-name. 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.
find-tables-by-name is provided by the Databricks Unity Catalog MCP Server MCP server (revodatanl/databricks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Databricks Unity Catalog MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Databricks Unity Catalog MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.