← All Python code MCP Servers Hub
bcb-mcp
An MCP server for the time series of the Central Bank of Brazil (BCB-SGS), with a curated series dictionary, a local parquet cache and DuckDB SQL for LLM agents. It is the Python counterpart of the R package GetBCBData.
Monthly downloads
142
PyPI downloads in the last 30 days.
All-time downloads
142
Cumulative downloads tracked from PyPI.
GitHub stars
★ 1
0 forks.
Last GitHub push
2026-11-10
Stats updated 2026-11-15
Install
Quickstart
# Run directly with uvx (recommended for MCP clients)
uvx bcb-mcp
# Or install from PyPI
pip install bcb-mcp
MCP Client Configuration
Add this entry to your claude_desktop_config.json or .cursor/mcp.json (or see the MCP Servers Hub for all three servers together):
{
"mcpServers": {
"bcb": {
"command": "uvx",
"args": [
"bcb-mcp"
]
}
}
}
What AI Agents Can Query
- Curated dictionary and search across BCB-SGS macroeconomic and financial series (Selic, IPCA, CDI, PTAX, GDP, credit)
- Time-series retrieval and summary statistics directly from the official Central Bank API
- Local Parquet caching with DuckDB SQL querying for fast multi-series analysis
Example Prompts
-
“Fetch monthly IPCA inflation and the Selic target rate from BCB-SGS since 2015 and calculate the real interest rate.”
-
“Search the BCB-SGS catalog for Brazilian USD/BRL exchange rate (PTAX) series and summarize annual averages since 2020.”
-
“Query the local cache with SQL to compare annual cumulative IPCA against CDI over the last 10 years.”
Companion & Counterpart Software
- R GetBCBData — R package counterpart for BCB-SGS time series
Cite this package
@manual{perlin_bcb_mcp,
author = {Perlin, Marcelo S.},
title = {bcb-mcp: An MCP server for the time series of the Central Bank of Brazil (BCB-SGS), with a curated series dictionary, a local parquet cache and DuckDB SQL for LLM agents. It is the Python counterpart of the R package GetBCBData.},
year = {2026},
note = {Python Model Context Protocol (MCP) server},
url = {https://github.com/msperlin/bcb-mcp}
}