langchain-webz

LangChain and LangGraph tools for Webz.io News Search.

This package does not hardcode search filters. It connects to the hosted MCP server and loads the live tool schema with tools/list. When the MCP adds a filter, agents see it on the next connection.

pip install langchain-webz
export WEBZ_API_TOKEN="your-webz-api-token"

Direct tool call

from langchain_webz import WebzNewsSearch

# env: WEBZ_API_TOKEN
tool = WebzNewsSearch()

# or pass the token in code
tool = WebzNewsSearch(api_token="your-webz-api-token")

print(tool.invoke({"query": "AI regulation Europe"}))

Agent / LangGraph

from langchain.agents import create_agent
from langchain_webz import get_webz_tools

tools = get_webz_tools()
agent = create_agent("openai:gpt-4.1-mini", tools)
result = agent.invoke({"messages": [{"role": "user", "content": "What is the latest EU AI news?"}]})
print(result["messages"][-1].content)

Inside an already running event loop, use the async helpers:

from langchain_webz import aget_webz_tools, awebz_news_search

tools = await aget_webz_tools()
tool = await awebz_news_search()

Config

You can also pass api_token= and mcp_url= to the helpers.

Get a token: https://webz.io