fund_job · Cardzero MCP: Risk & Policy

WHAT IT DOES

What fund_job does on Cardzero

AI agents use fund_job to commit financial operations through Cardzero — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why fund_job needs a policy

This tool moves real USDC funds by locking them into a smart-contract escrow. It commits financial obligations and transfers cryptocurrency, making it Financial category. The blast radius is critical because an AI agent misusing this tool could lock arbitrary amounts of USDC into escrow contracts on Base.

From the tool's definition Fund a Job created via create_job. Locks the budget USDC into escrow.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fund_job Approval-gated

Any call to fund_job is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fund_job": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Cardzero, so you can run agents against it safely.

FAQ

Questions about fund_job

What does the fund_job tool do? +

Fund a Job created via create_job. Locks the budget USDC into escrow. Requires that the Job is in. It is categorised as a Financial tool in the Cardzero MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on fund_job? +

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

What risk level is fund_job? +

fund_job is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit fund_job? +

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

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

fund_job is provided by the Cardzero MCP server (mrocker/cardzero-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.