cartridge_load · Cartridge MCP: Risk & Policy

WHAT IT DOES

What cartridge_load does on Cartridge

AI agents invoke cartridge_load to trigger actions in Cartridge. 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 cartridge_load needs a policy

Loading a cartridge doesn't just retrieve data; it changes the runtime environment by activating new tools, onboarding flows, and personality skins. This constitutes an execution-class action because it triggers external operations and makes new capabilities available. The blast radius is medium since a malicious or malformed cartridge could expose harmful tools or alter agent behavior significantly.

From the tool's definition 'Load a cartridge by ID, making its tools available' — loading a cartridge activates new tools and behaviors in the system, which is an operational/execution action rather than a simple read or write.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cartridge_load Rate-limited

cartridge_load 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": {
    "cartridge_load": {
      "limits": [
        {
          "counter": "cartridge_load_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 Cartridge, so you can run agents against it safely.

FAQ

Questions about cartridge_load

What does the cartridge_load tool do? +

Load a cartridge by ID, making its tools available. It is categorised as a Execute tool in the Cartridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cartridge_load? +

Register the Cartridge MCP server in PolicyLayer and add a rule for cartridge_load: 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 Cartridge. Nothing to install.

What risk level is cartridge_load? +

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

Can I rate-limit cartridge_load? +

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

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

cartridge_load is provided by the Cartridge MCP server (lucineer/cartridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.