config_path · Kaggle- MCP: Risk & Policy

WHAT IT DOES

What config_path does on Kaggle-MCP

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

WHY IT NEEDS A POLICY

Why config_path needs a policy

This tool modifies persistent configuration settings (the download path) but does not delete data, execute arbitrary code, or access financial systems. The modification is reversible (the path can be changed again), placing it squarely in the Write category.

From the tool's definition Tool description states 'Set or view the path where files will be downloaded.' The 'set' operation modifies configuration state, which is a write action. The 'view' operation is read-only, but the primary capability is setting/modifying the download path.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

config_path Rate-limited

config_path 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": {
    "config_path": {
      "limits": [
        {
          "counter": "config_path_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 Kaggle-MCP, so you can run agents against it safely.

FAQ

Questions about config_path

What does the config_path tool do? +

Set or view the path where files will be downloaded. It is categorised as a Write tool in the Kaggle-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on config_path? +

Register the Kaggle- MCP server in PolicyLayer and add a rule for config_path: 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 Kaggle-MCP. Nothing to install.

What risk level is config_path? +

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

Can I rate-limit config_path? +

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

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

config_path is provided by the Kaggle- MCP server (realbytecode/kaggle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.