AI agents call get_daraja_api_doc to retrieve information from Daraja API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves API documentation, which is a read-only information retrieval operation with no side effects. Even though the Daraja API itself handles financial transactions (M-Pesa payments), this specific tool only provides documentation about those APIs—it does not execute payments, modify data, or perform financial operations.
From the tool's definition Tool name 'get_daraja_api_doc' indicates retrieval of API documentation. Server context shows this is a documentation lookup service for Daraja/M-Pesa APIs.
Documented attack patterns abuse exactly the kind of access get_daraja_api_doc gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Daraja API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_daraja_api_doc:
{
"version": "1",
"default": "deny",
"tools": {
"get_daraja_api_doc": {}
}
}get_daraja_api_doc is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_daraja_api_doc. It is categorised as a Read tool in the Daraja API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Daraja API MCP Server MCP server in PolicyLayer and add a rule for get_daraja_api_doc: 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 Daraja API MCP Server. Nothing to install.
get_daraja_api_doc 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 get_daraja_api_doc 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 get_daraja_api_doc. 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.
get_daraja_api_doc is provided by the Daraja API MCP Server MCP server (jackscodevault/mpesa-daraja-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Daraja API MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Daraja API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.