Get the CREATE VIEW DDL statement for a view
AI agents call get_view_ddl to retrieve information from Querybridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata (the DDL/definition) of an existing view. This is a read-only operation that queries database schema information. It has no side effects, does not execute arbitrary code, and does not modify or delete data. The low severity reflects minimal blast radius — an agent could learn view definitions but cannot cause operational harm with this tool alone.
From the tool's definition Tool name is 'get_view_ddl' and description states 'Get the CREATE VIEW DDL statement for a view' — this retrieves the view definition without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get the CREATE VIEW DDL statement for a view. It is categorised as a Read tool in the Querybridge MCP Server, which means it retrieves data without modifying state.
Register the Querybridge MCP server in PolicyLayer and add a rule for get_view_ddl: 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 Querybridge. Nothing to install.
get_view_ddl 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_view_ddl 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_view_ddl. 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_view_ddl is provided by the Querybridge MCP server (mahmoudhassanmustafa/querybridge-mcp). 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 →