Skip to main content
A Noonum strategy turns an investment thesis into a ranked list of companies. Most of these guides walk through building, iterating on, analyzing, and integrating strategies, ordered from your first strategy to a full integration. The last one finds comparable companies by business overlap. All examples target the REST base URL https://api.noonum.ai/v2 or the MCP server at https://mcp.noonum.ai/mcp. Each request carries an Authorization: Bearer <token> header, where <token> is your Noonum API key. The MCP server also accepts OAuth sign-in with your Noonum account. If you are starting out, see the Quickstart and Authentication.

Guides

  • Build a strategy: turn an investment thesis into a ranked list of companies, from objective to submission to refinement. Most steps map to a REST endpoint and an MCP tool.
  • Iterate and refine a strategy: a Python workflow to enhance the objective, exclude unwanted companies, re-submit, and generate historical results.
  • Objective versioning: how submitting a changed draft creates an immutable version, where run results live, and how to list and poll versions.
  • Analyze and compare strategies: work with existing strategies. View holdings, find outliers, compare, refine, and export them via the REST API or MCP server.
  • End-to-end REST integration: a working tutorial with curl and Python side by side. Authenticate, use a public strategy from the catalog (GET /strategies?scope=public) or build your own, fetch holdings, and run a backtest.
  • Find comparable companies: find a company’s peers by business overlap, and start from an industry to find the companies in it. REST API only.
To connect an AI agent, see MCP client setup to point Claude, Cursor, or another client at the Noonum MCP server.

Need an API key?

To request an API key, see Authentication.