BC5 수금 3단계 — 입금 등록 → 인보이스 회수. collections_agent.register_payment 위임.
AI agents use register_collection_payment to commit financial operations through OOSDK MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool records an incoming payment and triggers invoice collection/recovery, which directly moves money or commits financial obligations. It is a financial transaction operation with high blast radius if misused — incorrect payment registration could result in financial discrepancies, double payments, or erroneous invoice closure.
From the tool's definition register_collection_payment — '입금 등록 → 인보이스 회수' (payment registration → invoice collection/recovery). Delegates to collections_agent.register_payment.
Attacks that exploit this kind of access
BC5 수금 3단계 — 입금 등록 → 인보이스 회수. collections_agent.register_payment 위임. It is categorised as a Financial tool in the OOSDK MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the OOSDK MCP Server MCP server in PolicyLayer and add a rule for register_collection_payment: 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 OOSDK MCP Server. Nothing to install.
register_collection_payment 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 register_collection_payment 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 register_collection_payment. 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.
register_collection_payment is provided by the OOSDK MCP Server MCP server (sunnylabtv-crypto/ai_mcp_multi_agent_oosdk-public). 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 →