Register C2B URLs for receiving M-Pesa payments directly.
AI agents use mpesa_c2b to create or update resources in Africa Payments MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Africa Payments MCP environment.
This tool registers callback URLs (Customer-to-Business) to receive M-Pesa payment notifications. It modifies configuration/endpoint settings on the M-Pesa platform — a reversible write operation. It does not itself move money, but misconfiguration could redirect payment notifications to a malicious endpoint, hence medium severity.
From the tool's definition Register C2B URLs for receiving M-Pesa payments directly
Attacks that exploit this kind of access
Register C2B URLs for receiving M-Pesa payments directly. It is categorised as a Write tool in the Africa Payments MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Africa Payments MCP server in PolicyLayer and add a rule for mpesa_c2b: 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_c2b is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mpesa_c2b 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_c2b. 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_c2b 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 →