How do I add fund and ETF data as a tool in LangChain or LangGraph?

A tool in twenty lines

python
# pip install langchain langchain-openai fundfacts
import os
from langchain_core.tools import tool
from fundfacts import FundFacts
​
ff = FundFacts()  # reads FUNDFACTS_API_KEY
​
@tool
def fund_facts(isin: str) -> dict:
    """Current factsheet of a fund or ETF by 12-character ISIN: name, TER, 1-7 risk
    indicator, category, fund size, top holdings, sector and country split,
    calendar and annualised returns, as-of date. Returns {"error": ...} when the
    ISIN is not a covered fund."""
    try:
        f = ff.get_fund(isin)
    except Exception as e:  # FundFactsError carries status and code
        return {"error": str(e)}
    d = f["data"]
    return {
        "name": f["name"], "category": d["profile"]["category"], "risk_1_to_7": d["riskRating"],
        "ter": d["headlineMetrics"]["ter"], "aum": d["keyFacts"]["aum"],
        "top_holdings": d["topHoldings"][:10], "sectors": d["sector"][:8], "countries": d["geography"][:8],
        "calendar_returns": d["calendarReturns"], "annualised_returns": d["annualisedReturns"],
        "as_of": d["dataAsOf"],
    }
​
@tool
def search_funds(query: str) -> list[dict]:
    """Find fund ISINs by name or issuer, e.g. 'msci world' or 'vanguard all-world'. Free."""
    return [{"isin": r["isin"], "name": r["name"], "issuer": r["issuer"]} for r in ff.search(query)["results"][:10]]

Bind the tools to a model and run an agent:

python
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
​
agent = create_react_agent(ChatOpenAI(model="gpt-4.1"), [fund_facts, search_funds],
    prompt="You answer questions about investment funds. Always quote as_of with figures. Say 'not disclosed' for empty fields; never estimate.")
result = agent.invoke({"messages": [("user", "What does IE00B4L5Y983 hold and what does it cost?")]})
print(result["messages"][-1].content)

Trimming the payload in the tool (the full one is a few kilobytes with the series) keeps the context small; return the whole data object if the agent needs the monthly series for calculations.

Or use the MCP server directly

python
# pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
​
client = MultiServerMCPClient({
    "fundfacts": {
        "transport": "streamable_http",
        "url": "https://fundfactsapi.com/api/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['FUNDFACTS_API_KEY']}"},
    }
})
tools = await client.get_tools()  # get_fund, search_funds, compare_funds, analyze_portfolio, fund_overlap, get_scpi

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.

Notes for production agents

• The first call for a cold ISIN can take up to a few minutes; give the tool a 300-second timeout and tell the model a first lookup can be slow.
• One request per ISIN answered. Cache tool results by ISIN until expiresAt if users repeat questions.
• The fund data for AI agents guide covers prompt design and guardrails in more depth.