Generate a Cypher query for Kuzu from natural language
AI agents invoke generateKuzuCypher to trigger actions in Kuzudb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool generates Cypher queries from natural language, which likely involves executing or preparing queries against the Kuzu database. Given the sibling 'query' tool exists for execution, this tool may only generate (not run) the query — however, generated queries could include destructive operations (DELETE, DROP).
From the tool's definition Generate a Cypher query for Kuzu from natural language
Documented attack patterns abuse exactly the kind of access generateKuzuCypher 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 generateKuzuCypher:
{
"version": "1",
"default": "deny",
"tools": {
"generateKuzuCypher": {
"limits": [
{
"counter": "generatekuzucypher_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}generateKuzuCypher stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate a Cypher query for Kuzu from natural language. It is categorised as a Execute tool in the Kuzudb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kuzudb MCP server in PolicyLayer and add a rule for generateKuzuCypher: 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.
generateKuzuCypher is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the generateKuzuCypher 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 generateKuzuCypher. 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.
generateKuzuCypher 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.