Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@wbgapi360 show me GDP growth for the US and China for the last 10 years"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
World Bank Data API client with two interfaces: A synchronous Python API for analysts, and a Model Context Protocol (MCP) server for AI agents.
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
pip install wbgapi360Optional extras:
# Visualization support (matplotlib + seaborn)
pip install "wbgapi360[visual]"
# Mapping support (geopandas + matplotlib)
pip install "wbgapi360[map]"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 %"
)After installation:
wbgapi360From repository source:
python -m wbgapi360.mcp.server{
"mcpServers": {
"worldbank": {
"command": "wbgapi360",
"args": []
}
}
}Tool | Description |
| Semantic search for indicator codes. |
| Retrieve time series data for one or many countries. |
| Compare countries across one or many indicators. |
| Return trend statistics (growth, volatility, direction). |
| Rank countries for an indicator globally or by region. |
| Generate chart images from JSON payloads. |
A separate CLI is provided for manual testing and quick queries:
wbgapi360-cli --helpCommands:
search
data
config
pip install -e ".[dev,visual]"
python -m pytest -q testsThis software is an independent open-source project. It is not affiliated with The World Bank Group.
wbgapi360 is inspired by Tim Herzog's original wbgapi project and extends it with MCP support and AI-focused workflows.
Maykol Medrano
Applied Economist / Policy Data Scientist
Email: mmedrano2@uc.cl
MIT. See LICENSE.
Analyze time-series trend with statistical insights.
Returns growth rates, volatility, trend direction, and more.
Inputs: economy (required), indicator (required), years, include_stats. Returns: result
Compare multiple countries across indicators.
Inputs: economies (required), indicators (required), years, normalize. Returns: result
Fetch World Bank data with auto-correction. Set labels=True for human-readable country names.
Inputs: economies (required), indicator_code (required), years, labels. Returns: result
Generate chart with FT style. Advanced: region (latam/africa/europe), bbox, bins, category_labels for map_categorical.
Inputs: data_json (required), chart_type (required), bbox, bins, +4 more. Returns: result
Rank countries by indicator value.
Inputs: indicator (required), top_n, region. Returns: result
Search for World Bank indicators using Smart Ranking.
Inputs: query (required), limit, database_id. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct purpose: searching indicators, fetching data, plotting, comparing, analyzing trends, and ranking. No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern in lowercase snake_case (search_indicators, get_data, plot_chart, compare_countries, analyze_trend, rank_countries). The naming is uniform and predictable.
With 6 tools, the server is well-scoped for a World Bank data analysis context. Each tool covers a distinct aspect of the workflow without being excessive or minimal.
The surface covers discovery, data retrieval, visualization, comparison, trend analysis, and ranking, which is solid. A minor gap is the lack of explicit country metadata or list endpoints, but this can often be worked around with known country codes.
World Bank MCP — wraps the World Bank Data API v2 (free, no auth)
Access World Bank development indicators for 200+ countries.
World Bank Data360 MCP — the World Bank's modern unified data platform.
Query 29,500+ World Bank development indicators for 200+ countries across 60+ years.