AI agents call get_job to retrieve information from Cardzero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval of existing Job state information without modifying, executing, or deleting any data. The public nature of Job state and absence of authentication requirements further confirm it poses minimal risk even if accessed by an untrusted AI agent.
From the tool's definition Tool description states 'Get the current state of a Job' with no side effects mentioned. It retrieves data (status, budget, transactions, evaluation outcome) and explicitly notes 'No authentication required — Job state is public', indicating a passive query…
Attacks that exploit this kind of access
Get the current state of a Job (status, budget, transactions, evaluation outcome). No authentication required — Job state is public. It is categorised as a Read tool in the Cardzero MCP Server, which means it retrieves data without modifying state.
Register the Cardzero MCP server in PolicyLayer and add a rule for get_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.
get_job 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 get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_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.
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 →