一个模型上下文协议（MCP）服务器，允许LLM代理直接访问世界银行的Data360平台。代理可以搜索、验证和检索发展指标——涵盖从GDP、贫困到性别平等和气候等主题——而无需误解数据值。

受众：开发者，开发AI代理和聊天机器人，需要可靠、结构化访问世界银行发展数据。

---

主要特色

• 智能指标发现 — 通过丰富的元数据和国家覆盖检查，跨数百个指标进行搜索
• 丰富的元数据检索 — 按需获取方法、定义、局限性及统计概念
• 可靠的时间序列数据——查询带有国家、时间段、性别、年龄和城市化过滤器的历史数据点
• LLM优化资源 — 内置系统提示、代码列表和聊天机器人集成的思维链指导
• 代理友好设计 — 重要的“粘合”逻辑使原始Data360 API可组合且安全用于大型语言模型工具

---

安装与版本固定

发布遵循语义版本控制;每个发布都会发布一个 vX.Y.Z 的 git 标签及对应的 GitHub 发布。

Data360 MCP Server

A Model Context Protocol (MCP) server that gives LLM agents direct access to the World Bank’s Data360 Platform. Agents can search, validate, and retrieve development indicators—covering topics from GDP and poverty to gender equality and climate—without hallucinating data values.

Audience: Developers building AI agents and chatbots that need reliable, structured access to World Bank development data.

---

Key Features

• Smart indicator discovery — search across hundreds of indicators with enriched metadata and country coverage checks
• Rich metadata retrieval — fetch methodology, definitions, limitations, and statistical concepts on demand
• Reliable time-series data — query historical data points with filters for country, time period, sex, age, and urbanization
• LLM-optimized resources — built-in system prompts, codelists, and chain-of-thought guidance for chatbot integration
• Agent-friendly design — significant “glue” logic makes the raw Data360 API composable and safe for LLM tool use

---

Installation & Version Pinning

Releases follow Semantic Versioning; every release publishes a vX.Y.Z git tag plus a corresponding GitHub Release. Minor releases keep backward-compatible API contracts, so pin a major/minor to lock behavior.

Install the Python server from PyPI and pin a known-good release:

pip install data360-mcp==0.1.3

Roll back to an earlier verified release by installing any prior version listed on the Releases page:

pip install data360-mcp==

The @data360/* npm UI packages are published on every release under the same version number; pin them the same way:

npm install @data360/[email protected]

See DEVELOPMENT.md for how releases are cut.

---

Prerequisites

• Python 3.11+
• uv (recommended) — or pip

Installation

With uv (recommended):

git clone https://github.com/worldbank/data360-mcp.git
cd data360-mcp
uv sync
# LangChain / LangGraph client + examples + repo-root shim (data360_mcp_service.py):
uv sync --extra agent --group dev

With pip:

git clone https://github.com/worldbank/data360-mcp.git
cd data360-mcp
pip install -e .

Configuration

Copy the example environment file and adjust as needed:

cp .env.example .env