NBIM MCP Server
MCP server for querying data from Norway's Government Pension Fund Global — the world's largest sovereign wealth fund.
README
NBIM MCP Server
MCP server for querying data from Norway's Government Pension Fund Global — the world's largest sovereign wealth fund.
What it does
Provides 6 tools for querying fund data through the Model Context Protocol:
| Tool | Description |
|---|---|
nbim_fund_value |
Current fund value and asset allocation breakdown |
nbim_holdings_search |
Search equity holdings by company, country, or sector |
nbim_top_holdings |
Top N holdings by market value with filters |
nbim_country_allocation |
Geographic allocation across 70+ countries |
nbim_returns |
Annual and cumulative returns since 1998 |
nbim_exclusions |
Companies excluded or under observation |
Install
pip install mcp-nbim
Or with uvx:
uvx mcp-nbim
Quick start
# Run with streamable HTTP (port 8008)
mcp-nbim
# Run with stdio (for Claude Desktop, Claude Code)
mcp-nbim --stdio
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"nbim": {
"command": "uvx",
"args": ["mcp-nbim", "--stdio"]
}
}
}
Or if installed with pip:
{
"mcpServers": {
"nbim": {
"command": "mcp-nbim",
"args": ["--stdio"]
}
}
}
Claude Code
claude mcp add nbim -- uvx mcp-nbim --stdio
Docker
docker compose up
Example queries
- "What is the fund worth today?" →
nbim_fund_value() - "Top 10 holdings in Japan" →
nbim_top_holdings(n=10, country='JP') - "Does the fund own Tesla?" →
nbim_holdings_search(query='Tesla') - "How has the US allocation changed?" → compare
nbim_country_allocation()across years - "Which companies are excluded for coal?" →
nbim_exclusions(criterion='coal') - "Fund performance in 2008" →
nbim_returns(start_year=2008, end_year=2008)
Data sources
- Holdings & fund value: NBIM Investment Data API (JSON, no auth required)
- Returns: Scraped from nbim.no/en/the-fund/returns/ with hardcoded fallback
- Exclusions: Scraped from nbim.no exclusion list
Holdings data updates semi-annually and covers equities (~9,000 companies). Historical data goes back to 1998. No authentication required.
Related
- Norges Bank MCP — Exchange rates, policy rate, yield curves
- Built by Gervi Labs
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。