Banxico MCP Server

Banxico MCP Server

Enables access to Bank of Mexico (Banxico) economic data including real-time and historical USD/MXN exchange rates, inflation data, interest rates, and other financial indicators. Supports querying current rates, historical data with date ranges, and economic metadata through natural language.

Category
Visit Server

README

Banxico MCP Server

A Model Context Protocol (MCP) server for accessing the Bank of Mexico (Banxico) SIE API to retrieve USD/MXN exchange rate data and other economic indicators.

License: MIT Python 3.10+

Features

  • Real-time Exchange Rates: Get the latest USD/MXN exchange rate from Banxico
  • Historical Data: Retrieve historical exchange rate data with customizable limits
  • Series Metadata: Access detailed information about economic data series
  • Date Range Queries: Get exchange rate data for specific date ranges
  • MCP Compatible: Works with Claude Desktop, Gemini CLI, and other MCP clients

Prerequisites

  1. Python 3.10+ installed on your system
  2. uvx (recommended) or uv package manager
  3. Banxico API Token - Get one from Banxico SIE API

Installation Methods

Option 1: Direct from GitHub (Auto-Updates) ⭐ Recommended

This method automatically gets the latest updates when you restart your MCP client:

Configuration for MCP clients:

"banxico": {
  "command": "uvx",
  "args": [
    "--from",
    "git+https://github.com/cfocoder/banxico_mcp",
    "banxico-mcp-server"
  ],
  "env": {
    "BANXICO_API_TOKEN": "your_token_here"
  }
}

No manual installation needed! uvx will automatically download and run the latest version.

Option 2: Download Single File (Manual Updates)

If you prefer to download the file locally:

  1. Install uvx (if not already installed):

    pip install uv
    
  2. Download the server file:

    curl -O https://raw.githubusercontent.com/cfocoder/banxico_mcp/main/banxico_mcp_server.py
    
  3. Configuration for MCP clients:

    "banxico": {
      "command": "uvx",
      "args": [
        "--python", "3.12",
        "--from", "fastmcp",
        "--with", "httpx",
        "--",
        "python",
        "/absolute/path/to/banxico_mcp_server.py"
      ],
      "env": {
        "BANXICO_API_TOKEN": "your_token_here"
      }
    }
    

    To get updates: Re-download the file when new features are added.

Option 3: Traditional Installation

  1. Clone the repository:

    git clone https://github.com/cfocoder/banxico_mcp.git
    cd banxico_mcp
    
  2. Install dependencies:

    pip install fastmcp httpx
    
  3. Run the server:

    BANXICO_API_TOKEN=your_token_here python banxico_mcp_server.py
    

Configuration

Get Your Banxico API Token

  1. Visit Banxico Token Registration
  2. Fill out the form to request an API token
  3. You'll receive your token via email

Configure MCP Clients

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "banxico": {
      "command": "uvx",
      "args": [
        "--python", "3.12",
        "--from", "fastmcp",
        "--with", "httpx",
        "--",
        "python",
        "/absolute/path/to/banxico_mcp_server.py"
      ],
      "env": {
        "BANXICO_API_TOKEN": "your_banxico_token_here"
      }
    }
  }
}

Gemini CLI

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "banxico": {
      "command": "uvx",
      "args": [
        "--python", "3.12",
        "--from", "fastmcp",
        "--with", "httpx",
        "--",
        "python",
        "/absolute/path/to/banxico_mcp_server.py"
      ],
      "env": {
        "BANXICO_API_TOKEN": "your_banxico_token_here"
      }
    }
  }
}

Available Tools

Tool Description Parameters
get_latest_usd_mxn_rate() Get the most recent USD/MXN exchange rate None
get_usd_mxn_historical_data(limit) Get historical exchange rate data limit: Max data points (default: 30)
get_series_metadata(series_id) Get metadata for a data series series_id: Series ID (default: SF63528)
get_date_range_data(start_date, end_date, series_id) Get data for specific date range start_date, end_date: YYYY-MM-DD format
get_inflation_data(inflation_type, limit) Get inflation data inflation_type: 'monthly', 'accumulated', 'annual' (default: 'monthly')<br>limit: Max data points (default: 12)
get_udis_data(limit) Get UDIS (Investment Units) values limit: Max data points (default: 30)
get_cetes_28_data(limit) Get CETES 28-day interest rates limit: Max data points (default: 30)
get_banxico_reserves_data(limit) Get Banxico Reserve Assets data limit: Max data points (default: 30)
get_unemployment_data(limit) Get unemployment rate data limit: Max data points (default: 24)

Usage Examples

Once configured with your MCP client, you can ask:

Exchange Rates:

  • "What's the current USD to MXN exchange rate?"
  • "Show me the USD/MXN exchange rate for the last 10 days"
  • "Get the exchange rate data from 2024-01-01 to 2024-01-31"
  • "What's the metadata for the USD/MXN series?"

Inflation Data:

  • "What's the current monthly inflation rate in Mexico?"
  • "Show me the annual inflation data for the last year"
  • "Get the accumulated inflation for the last 6 months"

Interest Rates:

  • "What are the current CETES 28-day rates?"
  • "Show me the CETES rates for the last month"

Financial Indicators:

  • "What are the current UDIS values?"
  • "Show me Banxico's reserve assets"
  • "Get the latest financial indicators from Banxico"

Labor Market:

  • "What's the current unemployment rate in Mexico?"
  • "Show me unemployment trends for the last year"
  • "How has unemployment changed over the last 2 years?"

API Reference

The server uses the Banxico SIE API with the following endpoints:

Exchange Rates:

  • Latest Data: /series/SF63528/datos/oportuno
  • Historical Data: /series/SF63528/datos
  • Series Metadata: /series/SF63528
  • Date Range: /series/SF63528/datos/{start_date}/{end_date}

Inflation Data:

  • Monthly Inflation: /series/SP30577/datos
  • Accumulated Inflation: /series/SP30579/datos
  • Annual Inflation: /series/SP30578/datos

Financial Indicators:

  • UDIS: /series/SP68257/datos
  • CETES 28-day: /series/SF282/datos
  • Banxico Reserves: /series/SF308843/datos

Labor Market:

  • Unemployment Rate: /series/SL1/datos

Development

Project Structure

banxico-mcp-server/
├── banxico_mcp_server.py    # Main server file
├── README.md                # This file
├── LICENSE                  # MIT License
├── CONTRIBUTING.md          # Development guidelines
└── docs/                    # Documentation and examples
    ├── EXTENDING.md         # Guide for adding new endpoints
    └── examples/            # Configuration examples
        ├── claude-desktop.md
        ├── continue.md
        ├── env-template.md
        ├── gemini-cli.md
        └── vscode-cline.md

Testing

To test the server without an MCP client:

# Set your token
export BANXICO_API_TOKEN=your_token_here

# Run the server with a timeout to test startup
timeout 5s python banxico_mcp_server.py && echo "Server starts successfully"

Adding New Tools

See EXTENDING.md for detailed instructions on adding new Banxico API endpoints.

Troubleshooting

Common Issues

  1. "BANXICO_API_TOKEN environment variable not set"

    • Ensure your API token is properly configured in the MCP client settings
  2. "Failed to retrieve data"

    • Check your internet connection
    • Verify your API token is valid
    • Ensure the Banxico API is accessible
  3. Server doesn't start

    • Verify Python 3.10+ is installed
    • Check that uvx or required dependencies are available

Debug Mode

Run with debug logging:

BANXICO_API_TOKEN=your_token PYTHONPATH=. python -c "
import logging
logging.basicConfig(level=logging.DEBUG)
from banxico_mcp_server import mcp
mcp.run()
"

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Related Projects

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured