How do I give an n8n AI Agent access to fund data?

HTTP Request Tool

1. Add an AI Agent node with your chat model.
2. Under Tools, add HTTP Request Tool:

- Description: Current factsheet of a fund or ETF by 12-character ISIN: name, TER, risk 1-7, holdings, sector and country split, returns, as-of date. - Method GET, URL https://fundfactsapi.com/api/v1/funds/{isin} with the isin placeholder set to "let the model define". - Authentication: Generic → Header Auth, name Authorization, value Bearer ffk_.... - Options → Timeout 300000 (a cold ISIN can take minutes on first load).

1. Optionally add a second tool for https://fundfactsapi.com/api/v1/search?q={query} (free) so the agent can resolve names to ISINs.

Keep the system message short: "Use the tools for any fund question. Quote dataAsOf with figures. Empty fields mean not disclosed."

MCP Client Tool

The MCP Client Tool node connects the agent to a remote server:

The MCP server exposes six tools, each counted like the REST endpoint it wraps: get_fund (ISIN → the full factsheet payload), search_funds (name → ISINs, free), compare_funds (side-by-side table for several ISINs), analyze_portfolio (weighted look-through of a list of positions, Pro and above), fund_overlap (shared holdings between funds, Pro and above) and get_scpi (French SCPI data by name or ISIN). Authentication is the same bearer API key as the REST API, sent as an Authorization header.

Cost

One request per ISIN answered, exactly like calling the REST endpoint from an ordinary HTTP Request node. The n8n lookup page shows the non-agent version with a ready-to-paste workflow.