AI agents call getSchema to retrieve information from Kuzudb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves schema metadata from the database, which is a passive read operation with no side effects. It does not execute queries on data, modify records, delete information, or trigger external operations. The blast radius of misuse is minimal since schema information is typically non-sensitive structural metadata.
From the tool's definition Tool name is 'getSchema' and description states 'Get the schema of the Kuzu database' - this is a read-only retrieval operation that inspects database structure without modifying or executing operations on data.
Documented attack patterns abuse exactly the kind of access getSchema gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kuzudb, and nothing reaches the server without passing your rules. This is the rule we recommend for getSchema:
{
"version": "1",
"default": "deny",
"tools": {
"getSchema": {}
}
}getSchema 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.
Get the schema of the Kuzu database. It is categorised as a Read tool in the Kuzudb MCP Server, which means it retrieves data without modifying state.
Register the Kuzudb MCP server in PolicyLayer and add a rule for getSchema: 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 Kuzudb. Nothing to install.
getSchema 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 getSchema 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 getSchema. 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.
getSchema is provided by the Kuzudb MCP server (jordanburke/kuzudb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kuzudb, 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.
3 Kuzudb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.