Skip to main content
Glama
cfocoder

Banxico MCP Server

get_udis_data

Retrieve current and historical UDIS (Investment Units) data from Mexico's central bank. Specify a limit to control the number of recent data points returned.

Instructions

Get UDIS (Investment Units) data from Banxico.

Args: limit: Maximum number of recent data points (default: 30)

Returns: Current and historical UDIS values

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo

Implementation Reference

  • The get_udis_data tool handler, registered via @mcp.tool() decorator. Fetches UDIS data from Banxico SIE API endpoint 'series/SP68257/datos', applies optional limit to recent data points, and formats the response using format_exchange_rate_data.
    @mcp.tool() async def get_udis_data(limit: Optional[int] = 30) -> str: """ Get UDIS (Investment Units) data from Banxico. Args: limit: Maximum number of recent data points (default: 30) Returns: Current and historical UDIS values """ if not BANXICO_TOKEN: return "Error: BANXICO_API_TOKEN environment variable not set. Please configure your API token." endpoint = "series/SP68257/datos" data = await make_banxico_request(endpoint, BANXICO_TOKEN) if not data: return "Failed to retrieve UDIS data. Please check your API token and network connection." # Apply limit if specified if limit and data.get("bmx", {}).get("series"): for series in data["bmx"]["series"]: if "datos" in series and len(series["datos"]) > limit: series["datos"] = series["datos"][-limit:] return format_exchange_rate_data(data)
  • Registration of the get_udis_data tool using FastMCP's @mcp.tool() decorator, which also derives schema from function signature and docstring.
    @mcp.tool()
  • Helper function used by get_udis_data to make authenticated HTTP requests to Banxico API.
    async def make_banxico_request(endpoint: str, token: str) -> dict[str, Any] | None: """ Make a request to the Banxico SIE API with proper error handling. Args: endpoint: The API endpoint to call (without base URL) token: The Banxico API token Returns: JSON response data or None if request failed """ url = f"{BANXICO_API_BASE}/{endpoint}" headers = {"User-Agent": USER_AGENT} params = {"token": token} try: async with httpx.AsyncClient() as client: response = await client.get(url, headers=headers, params=params, timeout=30.0) response.raise_for_status() return response.json() except httpx.HTTPError as e: logger.error(f"HTTP error occurred: {e}") return None except Exception as e: logger.error(f"An error occurred: {e}") return None
  • Helper function used by get_udis_data to format the API response data into a readable string representation.
    def format_exchange_rate_data(data: dict[str, Any]) -> str: """ Format exchange rate data into a readable string. Args: data: Raw JSON response from Banxico API Returns: Formatted string with exchange rate information """ if not data or "bmx" not in data: return "No data available" series_list = data["bmx"].get("series", []) if not series_list: return "No series data found" result = [] for series in series_list: series_title = series.get("titulo", "Unknown Series") series_id = series.get("idSerie", "Unknown ID") result.append(f"Series: {series_title} (ID: {series_id})") datos = series.get("datos", []) if not datos: result.append(" No data points available") else: result.append(f" Total data points: {len(datos)}") # Show first few and last few data points if len(datos) <= 10: for dato in datos: fecha = dato.get("fecha", "Unknown date") valor = dato.get("dato", "N/A") result.append(f" {fecha}: {valor}") else: # Show first 5 for i, dato in enumerate(datos[:5]): fecha = dato.get("fecha", "Unknown date") valor = dato.get("dato", "N/A") result.append(f" {fecha}: {valor}") result.append(f" ... ({len(datos) - 10} more data points) ...") # Show last 5 for dato in datos[-5:]: fecha = dato.get("fecha", "Unknown date") valor = dato.get("dato", "N/A") result.append(f" {fecha}: {valor}") result.append("") # Empty line between series return "\n".join(result)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cfocoder/banxico_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server