How do I add sanctions screening to a LangChain agent?

Steps

1. Install langchain-strale and a chat-model package.
2. Create the toolkit with your Strale API key.
3. Bind sanctions-check to your model.
4. Ask it to screen a name and run the tool call the model returns.

The solution

# pip install langchain-strale langchain-openai
from langchain_strale import StraleToolkit
from langchain_openai import ChatOpenAI

toolkit = StraleToolkit(api_key="sk_live_YOUR_KEY")
tools = [t for t in toolkit.get_tools() if t.name == "sanctions-check"]

llm = ChatOpenAI(model="gpt-4o").bind_tools(tools)
result = llm.invoke("Screen 'Acme Corporation' against international sanctions lists")

# The model picks the tool and its arguments; your code runs the call.
for call in result.tool_calls:
    tool = next(t for t in tools if t.name == call["name"])
    print(tool.invoke(call["args"]))

How it works

The tool searches the consolidated sanctions and debarment lists that Dilisense maintains, including the US OFAC SDN list, the EU financial sanctions list, the UN Security Council list and the UK sanctions list. The tool page names the sources. It matches names approximately and returns is_sanctioned, match_count and a matches list.

Each match has the listed name, the lists it appears on, the countries involved and the listing details. There is no numeric confidence score. Common names can match the wrong person or company, so pass country, and birth_date for a person, to narrow the search.

Every answer includes lists_queried, which names the lists searched, so you can show what was checked.

A match means a name appears on a list that was searched. It is not a decision about the person or company: a person should review it.

bind_tools only lets the model propose a call. To have the model read the result and answer in words, put the same tools in one of LangChain's agent loops.

Tools in this guide