run_look · Looker MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_look does on Looker MCP Server

AI agents invoke run_look to trigger actions in Looker MCP Server. 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_look needs a policy

Running a Look executes a query against potentially sensitive business data with effects that depend on what the Look contains (filters, joins, aggregations). While not irreversible like Destructive tools, execution carries risk of data exposure, resource exhaustion, or triggering downstream processes.

From the tool's definition Tool name 'run_look' combined with server description stating it 'enables querying the semantic model' indicates execution of predefined or ad-hoc queries against Looker's data model.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_look Rate-limited

run_look 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_look": {
      "limits": [
        {
          "counter": "run_look_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 Looker MCP Server, so you can run agents against it safely.

FAQ

Questions about run_look

What does the run_look tool do? +

run_look. It is categorised as a Execute tool in the Looker MCP Server 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_look? +

Register the Looker MCP Server MCP server in PolicyLayer and add a rule for run_look: 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 Looker MCP Server. Nothing to install.

What risk level is run_look? +

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

Can I rate-limit run_look? +

Yes. Add a rate_limit block to the run_look 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_look completely? +

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

run_look is provided by the Looker MCP Server MCP server (ultrathink-solutions/looker-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.