query_lakehouse · Duckdb Iceberg MCP: Risk & Policy

WHAT IT DOES

What query_lakehouse does on Duckdb Iceberg

AI agents invoke query_lakehouse to trigger actions in Duckdb Iceberg. 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.

WHY IT NEEDS A POLICY

Why query_lakehouse needs a policy

The tool executes arbitrary SQL queries against S3-backed Iceberg tables via DuckDB. While the description hints at read-oriented functions (read_parquet, iceberg_scan), 'Execute a SQL query' with no explicit read-only constraint means an AI agent could potentially run destructive or mutating SQL.

From the tool's definition 'Execute a SQL query' — the tool runs arbitrary SQL via DuckDB, which can include not just SELECT but also DML/DDL operations depending on DuckDB's permissions and the underlying storage access.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_lakehouse Rate-limited

query_lakehouse 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_lakehouse": {
      "limits": [
        {
          "counter": "query_lakehouse_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Duckdb Iceberg, so you can run agents against it safely.

FAQ

Questions about query_lakehouse

What does the query_lakehouse tool do? +

Execute a SQL query. Use read_parquet() or iceberg_scan() for S3 paths,. It is categorised as a Execute tool in the Duckdb Iceberg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_lakehouse? +

Register the Duckdb Iceberg MCP server in PolicyLayer and add a rule for query_lakehouse: 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 Duckdb Iceberg. Nothing to install.

What risk level is query_lakehouse? +

query_lakehouse is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_lakehouse? +

Yes. Add a rate_limit block to the query_lakehouse 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.

How do I block query_lakehouse completely? +

Set action: deny in the PolicyLayer policy for query_lakehouse. 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.

What MCP server provides query_lakehouse? +

query_lakehouse is provided by the Duckdb Iceberg MCP server (ys1173/duckdb-iceberg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.