DarajaMCP provides a bridge to the Safaricom M-Pesa mobile payment API, enabling AI assistants to initiate STK Push transactions directly from conversations. Built on FastMCP, it handles authentication with the Daraja API and manages the complete payment flow, from generating access tokens to processing transaction requests. The implementation is particularly valuable for applications requiring seamless mobile payment integration in Kenya, allowing users to authorize payments on their mobile devices without leaving their conversation with an AI assistant.
Initiate an M-Pesa STK push request to prompt the customer to authorize a payment on their mobile device. Inputs: amount (int), phone_number (int). Returns: JSON formatted M-PESA API response.
Generate a QR code for a payment request that customers can scan to make payments. Inputs: merchant_name (str), transaction_reference_no (str), amount (int), transaction_type (Literal["BG", "WA", "PB", "SM", "SB"]), credit_party_identifier (str). Returns: JSON formatted M-PESA API response containing the QR code data.
Create a connector from data source to unstructured server for processing. Inputs: connector_name (str). Returns: Source connector details including name and ID.
Create a connector from unstructured server to destination for data storage. Inputs: connector_name (str). Returns: Destination connector details including name and ID.
Create a workflow to process data from source connector to destination connector. Inputs: workflow_name (str), source_id (str), destination_id (str). Returns: Workflow details including name, ID, status, type, sources, destinations, and schedule.
Execute a workflow. Inputs: workflow_id (str). Returns: Workflow execution status.
Get detailed information about a workflow. Inputs: workflow_id (str). Returns: Workflow details including name, ID, and status.
Fetch documents analyzed during workflow execution. Inputs: None. Returns: List of analyzed documents.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIOur bundler currently only supports TypeScript-based servers. Check back soon!