agent_status
Report whether this agent can underwrite right now: key, USDC balance on the payment chain, whether the auditor is answering, what the budget has left, and the single next step to take. Call this first, and whenever a paid tool refuses.
This record as markdown: /tools/0x402-mcp/agent-status.md
What agent_status does on 0x402
AI agents call agent_status to retrieve information from 0x402 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why agent_status is rated Low
Even though agent_status only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs agent_status safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0x402, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_status, this is the rule to start with:
agent_status is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0x402, apply this rule, and every agent_status call is checked against it from then on.
Questions about agent_status
Report whether this agent can underwrite right now: key, USDC balance on the payment chain, whether the auditor is answering, what the budget has left, and the single next step to take. Call this first, and whenever a paid tool refuses. It is categorised as a Read tool in the 0x402 MCP Server, which means it retrieves data without modifying state.
Register the 0x402 MCP server in PolicyLayer and add a rule for agent_status: 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 0x402. Nothing to install.
agent_status 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 agent_status 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 agent_status. 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.
agent_status is provided by the 0x402 MCP server (@0x402/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0x402, and thousands of servers like it.
This server
Across the catalogue