AI agents use agent_session to commit financial operations through CorteX402 — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The server context makes clear that all tools on this server involve on-chain USDC payments settled per call on Base mainnet. Even though the tool description is empty, 'agent_session' in this context most likely establishes or manages a session that authorizes and enables subsequent financial transactions (pay-per-call settlements).
From the tool's definition Server description states 'Every call settles in USDC with an on-chain receipt' and references 'agent session auth' as a pay-per-call product on Base mainnet. The tool name 'agent_session' suggests it manages session authentication for these paid calls.
Attacks that exploit this kind of access
agent_session. It is categorised as a Financial tool in the CorteX402 MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the CorteX402 MCP server in PolicyLayer and add a rule for agent_session: 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 CorteX402. Nothing to install.
agent_session is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the agent_session 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_session. 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_session is provided by the CorteX402 MCP server (ooak21/cortex402-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 →