run_query · Mcp Bauplan MCP: Risk & Policy

WHAT IT DOES

What run_query does on Mcp Bauplan

AI agents invoke run_query to trigger actions in Mcp Bauplan. 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 run_query needs a policy

Although the description mentions SELECT queries specifically, execute-class tools run code/commands with blast radius dependent on the query argument. The tool permits executing arbitrary SQL against production Iceberg tables, making it Execute rather than Read. No evidence limits it to SELECT-only enforcement, so it cannot be safely assumed read-only.

From the tool's definition Tool executes SQL queries ('run_query' and 'executing SQL queries') against live data tables in S3. The description explicitly states the server 'enables users to...run SELECT queries', indicating arbitrary query execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_query Rate-limited

run_query 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": {
    "run_query": {
      "limits": [
        {
          "counter": "run_query_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 Mcp Bauplan, so you can run agents against it safely.

FAQ

Questions about run_query

What does the run_query tool do? +

Query the Bauplan data store using SQL. It is categorised as a Execute tool in the Mcp Bauplan MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_query? +

Register the Mcp Bauplan MCP server in PolicyLayer and add a rule for run_query: 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 Mcp Bauplan. Nothing to install.

What risk level is run_query? +

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

Can I rate-limit run_query? +

Yes. Add a rate_limit block to the run_query 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 run_query completely? +

Set action: deny in the PolicyLayer policy for run_query. 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 run_query? +

run_query is provided by the Mcp Bauplan MCP server (marcoeg/mcp-bauplan). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.