wbgapi360

World Bank Data API client with two interfaces: A synchronous Python API for analysts, and a Model Context Protocol (MCP) server for AI agents.

What You Get

• Smart indicator discovery (search) with heuristic ranking.

• High-level data retrieval (get_data) with code normalization.

• Publication-style charts (plot) with optional visual dependencies.

• MCP tools for search, data access, comparisons, trend analysis, rankings, and chart generation.

Related MCP server: Countries MCP Server

Installation

pip install wbgapi360

Optional extras:

# Visualization support (matplotlib + seaborn)
pip install "wbgapi360[visual]"

# Mapping support (geopandas + matplotlib)
pip install "wbgapi360[map]"

Python API (Analysts)

import wbgapi360 as wb

# 1) Search indicators
results = wb.search("inflation")
for r in results[:3]:
    print(f"[{r['code']}] {r['name']}")

# 2) Fetch data
df = wb.get_data(
    indicator="NY.GDP.MKTP.KD.ZG",
    economies=["USA", "CHN", "PER"],
    years=10
)
print(df.head())

# 3) Plot (requires: pip install "wbgapi360[visual]")
wb.plot(
    chart_type="trend",
    data=df,
    title="GDP Growth",
    subtitle="Annual %"
)

MCP Server (AI Agents)

Run the server

After installation:

wbgapi360

From repository source:

python -m wbgapi360.mcp.server

Claude Desktop example

{
  "mcpServers": {
    "worldbank": {
      "command": "wbgapi360",
      "args": []
    }
  }
}

MCP tools

CLI (Developer Utility)

A separate CLI is provided for manual testing and quick queries:

wbgapi360-cli --help

Commands:

• search

• data

• config

Development

pip install -e ".[dev,visual]"
python -m pytest -q tests

Project Notes

Unofficial client

This software is an independent open-source project. It is not affiliated with The World Bank Group.

Attribution

wbgapi360 is inspired by Tim Herzog's original wbgapi project and extends it with MCP support and AI-focused workflows.

Author

Maykol Medrano
Applied Economist / Policy Data Scientist
Email: mmedrano2@uc.cl

License

MIT. See LICENSE.