AI agents call list_databases to retrieve information from Spark SQL without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only metadata discovery, returning a list of existing databases. It has no side effects, does not execute queries against data, and does not modify any state. The blast radius of misuse is minimal—an attacker gains only informational awareness of database structure, which is typically non-sensitive compared to actual data access or execution capabilities.
From the tool's definition Tool name 'list_databases' combined with description 'List all available databases in the Spark cluster' indicates a query operation that retrieves metadata without modifying data or executing arbitrary code.
Attacks that exploit this kind of access
List all available databases in the Spark cluster. It is categorised as a Read tool in the Spark SQL MCP Server, which means it retrieves data without modifying state.
Register the Spark SQL MCP server in PolicyLayer and add a rule for list_databases: 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 Spark SQL. Nothing to install.
list_databases 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_databases 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_databases. 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_databases is provided by the Spark SQL MCP server (spark-sql-mcp-server). 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 →