manage_cache · MCP BigQuery Server MCP: Risk & Policy

WHAT IT DOES

What manage_cache does on MCP BigQuery Server

AI agents use manage_cache to create or update resources in MCP BigQuery Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP BigQuery Server environment.

WHY IT NEEDS A POLICY

Why manage_cache needs a policy

This tool modifies cache state through cleanup and invalidation operations, making it a Write action with destructive aspects. However, since cache invalidation is typically reversible (cache can be repopulated on next query) and does not permanently destroy source data, it is classified as Write rather than Destructive.

From the tool's definition 'Comprehensive cache management operations including statistics, cleanup, and targeted invalidation' indicates modify/delete operations on cached data via 'cleanup' and 'invalidation', which are Write/Destructive in nature.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_cache Rate-limited

manage_cache stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "manage_cache": {
      "limits": [
        {
          "counter": "manage_cache_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 BigQuery Server, so you can run agents against it safely.

FAQ

Questions about manage_cache

What does the manage_cache tool do? +

Comprehensive cache management operations including statistics, cleanup, and targeted invalidation. It is categorised as a Write tool in the MCP BigQuery Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_cache? +

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

What risk level is manage_cache? +

manage_cache is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit manage_cache? +

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

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

manage_cache is provided by the MCP BigQuery Server MCP server (mousten/mcp-bigquery-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.