sum_last_n_topups
AI agents call sum_last_n_topups to retrieve information from Africa's Talking Airtime MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to compute a sum across the last N top-up transactions—a read operation that retrieves and aggregates historical data without modifying state. The absence of a description lowers confidence slightly, but the naming convention and context of analytics/history-viewing operations strongly suggest it is a query rather than a write, execute, or destructive action.
From the tool's definition Tool name 'sum_last_n_topups' indicates aggregation of historical transaction data. Server description lists 'analyze top-up patterns' and 'view transaction history' as read operations.
Attacks that exploit this kind of access
sum_last_n_topups. It is categorised as a Read tool in the Africa's Talking Airtime MCP MCP Server, which means it retrieves data without modifying state.
Register the Africa's Talking Airtime MCP server in PolicyLayer and add a rule for sum_last_n_topups: 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's Talking Airtime MCP. Nothing to install.
sum_last_n_topups 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 sum_last_n_topups 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 sum_last_n_topups. 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.
sum_last_n_topups is provided by the Africa's Talking Airtime MCP server (nasoma/africastalking-airtime-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 →