AI agents call cartridge_onboard to retrieve information from Cartridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and returns onboarding information without creating, modifying, deleting, executing code, or committing financial obligations. It functions as a query/fetch operation with no side effects, placing it squarely in the Read category with low severity risk.
From the tool's definition The tool description states 'Get onboarding info for a cartridge', which is a retrieval operation that returns information about cartridge onboarding flows tailored for different user types (human or agent).
Attacks that exploit this kind of access
Get onboarding info for a cartridge (tailored for human or agent). It is categorised as a Read tool in the Cartridge MCP Server, which means it retrieves data without modifying state.
Register the Cartridge MCP server in PolicyLayer and add a rule for cartridge_onboard: 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.
cartridge_onboard is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cartridge_onboard 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.
Set action: deny in the PolicyLayer policy for cartridge_onboard. 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.
cartridge_onboard 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →