AI agents call get-databases-tool to retrieve information from Sql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves database names and metadata from SQL Server without creating, modifying, or deleting any data. The operation has no side effects and only exposes schema information that may already be accessible through standard database connection methods. The risk is low as the blast radius of misuse is limited to information disclosure of database names.
From the tool's definition Tool name 'get-databases-tool' and description 'Lists available databases on the SQL Server' indicate a query operation that retrieves metadata without modification or execution of commands.
Attacks that exploit this kind of access
Lists available databases on the SQL Server. It is categorised as a Read tool in the Sql MCP Server, which means it retrieves data without modifying state.
Register the Sql MCP server in PolicyLayer and add a rule for get-databases-tool: 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 Sql. Nothing to install.
get-databases-tool 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 get-databases-tool 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 get-databases-tool. 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.
get-databases-tool is provided by the Sql MCP server (prahveent/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 →