mcpField
R
remit-mcp

remit-mcp

Local
github.com/gabrielmahiaFinance0Updated 3d ago
Repository

About remit-mcp

remit-mcp is an MCP server for comparing remittance corridors from the US, UK, and Canada to Kenya. It provides provider comparisons and annual savings estimates using synthetic demo prices, not data for operational decisions.

Key features

  1. 01Compare US, UK, and Canada to Kenya corridors
  2. 02Estimate annual savings from switching providers
  3. 03List supported remittance corridors

Use cases

  1. 01Compare provider prices on supported corridors
  2. 02Estimate potential savings from changing providers

MCP support

As an MCP server, it exposes tools for corridor comparisons, savings estimates, and listing supported corridors. Its prices are synthetic demo data, not World Bank figures.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gabrielmahia-remit": {
      "command": "uvx",
      "args": [
        "remit-mcp"
      ]
    }
  }
}
Run commanduvx remit-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiremit-mcp0.1.8

Tools

3

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
corridorstringYesCorridor code: US_KE, UK_KE, CA_KE
amount_usdnumberNoAmount in USD to send (or equivalent)

Details

From the project README

💸 remit-mcp

remit-mcp Glama score smithery badge

Install: pip install remit-mcp · Use with any MCP client.

Remittance corridor fees to East Africa often run well above the UN SDG 10.c target of 3% by 2030 — but comparing corridors requires checking each provider manually.

pip install remit-mcp
remit-mcp

Tools

ToolWhat it does
compare_remittance_corridorsCompare all providers for US→KE, UK→KE, CA→KE corridors
estimate_savingsCalculate annual savings by switching providers
list_corridorsList all supported corridors

Research Basis

  • World Bank Remittance Prices Worldwide is the database to check real corridor costs against (SDG 10.c target: 3% by 2030). This server's corridor prices are synthetic and are not World Bank figures.
  • Central Bank of Kenya: Kenya received USD 4.94 billion in remittances in calendar 2024 (USD 4.18 billion in 2023), reported by Business Daily; a record USD 5.08 billion in FY2024/25; the CBK's own release puts 2024 at Ksh 666.7 billion, about 4% of GDP. (An earlier version of this README said USD 4.2 billion for 2024, which was the 2023 level.)

Context: PAPSS and Pesalink (2026), not modelled here

In February 2026 Kenya's Pesalink instant-payment network linked to the Pan-African Payment and Settlement System (PAPSS), so that PAPSS participants can send into Kenyan banks and mobile-money wallets in local currency (source: PAPSS and Pesalink announcements, 26 Feb 2026). This server compares US, UK and Canada corridors only; it does not model intra-African or PAPSS routes.

DEMO Note

Current data is synthetic, representative of World Bank RPW Kenya corridor patterns. Real implementation queries: remittanceprices.worldbank.org API + live FX feeds.

© 2026 Gabriel Mahia / AI Kung Fu LLC · MIT License

Part of the East Africa Coordination Stack

This MCP server is part of the Kenya coordination infrastructure. Connect it to africa-coord-bus — the coordination event bus that routes signals between domains automatically.

pip install africa-coord-bus

All servers: pypi.org/user/gmahia Live demo: coord-cascade-demo

IP & Collaboration

MIT licensed. Feedback via GitHub Issues only — pull requests are not accepted. Demo data is labeled DEMO and is not suitable for operational decisions. Full policy: docs/architecture/IP_POLICY.md. Security reports: see SECURITY.md.

Part of the East Africa coordination stack

Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.