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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.