Generate a Mermaid ER diagram from the database schema
AI agents call generate_erd 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.
This tool introspects the database schema to generate a visual ER diagram in Mermaid format. It only reads structural metadata (tables, columns, relationships) and produces a diagram output. No data is modified, deleted, or executed. Severity is low as misuse would at most expose schema structure.
From the tool's definition 'Generate a Mermaid ER diagram from the database schema' — reads schema metadata to produce a diagram with no side effects
Attacks that exploit this kind of access
Generate a Mermaid ER diagram from the database schema. 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 generate_erd: 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.
generate_erd 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 generate_erd 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 generate_erd. 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.
generate_erd 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 →