Send money from business to customer (B2C). Used for payouts, refunds, salaries.
AI agents use mpesa_b2c to commit financial operations through Africa Payments MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly transfers funds from a business account to customer accounts, which constitutes a financial transaction. Misuse by an AI agent could result in unauthorized money transfers, fraud, or depletion of business funds.
From the tool's definition Tool description explicitly states 'Send money from business to customer (B2C). Used for payouts, refunds, salaries.' The function moves actual money between accounts.
Attacks that exploit this kind of access
Send money from business to customer (B2C). Used for payouts, refunds, salaries. It is categorised as a Financial tool in the Africa Payments MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Africa Payments MCP server in PolicyLayer and add a rule for mpesa_b2c: 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 Africa Payments MCP. Nothing to install.
mpesa_b2c 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 mpesa_b2c 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 mpesa_b2c. 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.
mpesa_b2c is provided by the Africa Payments MCP server (kenyaclaw/africa-payments-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 →