AgentStack
MCP verified MIT Self-run

Mcp Wbgapi360

mcp-maykolmedrano-mcp-wbgapi360 · by MaykolMedrano

Enterprise-grade Async Python Client for World Bank Data360 API with hybrid MCP support for AI Agents (Claude/OpenAI).

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add mcp-maykolmedrano-mcp-wbgapi360

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Mcp Wbgapi360? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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.

[](https://pypi.org/project/wbgapi360/) [](https://www.python.org/downloads/) [](https://github.com/MaykolMedrano/mcp_wbgapi360/actions/workflows/ci.yml) [](https://pypi.org/project/wbgapi360/) [](https://opensource.org/licenses/MIT)


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.

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.run

Claude Desktop example

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

MCP tools

| Tool | Description | | :--- | :--- | | search_indicators | Semantic search for indicator codes. | | get_data | Retrieve time series data for one or many countries. | | compare_countries | Compare countries across one or many indicators. | | analyze_trend | Return trend statistics (growth, volatility, direction). | | rank_countries | Rank countries for an indicator globally or by region. | | plot_chart | Generate chart images from JSON payloads. |

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](mailto:mmedrano2@uc.cl)

License

MIT. See LICENSE.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.