llama-index-tools-webz

Search global news with Webz.io from Python - in natural language, with the most relevant articles first.

Webz.io News Search covers news and current events from sources worldwide. Ask a question in plain language, narrow results with filters (language, country, date, sentiment, domain, ticker, and more), and get back focused article excerpts with titles, URLs, and metadata.

Use this package on its own, or plug it into LlamaIndex agents.

What you get

• Natural-language search - no keyword hacking. Example: "EU AI Act enforcement updates" or "How is Tesla stock reacting to earnings?"
• Worldwide coverage - semantic search over Webz.io's global news index.
• Rich filters - language, country, days, sentiment, domain, ticker, person, organization, topic, and more. See the MCP tool reference.
• Live schema - filters are loaded from the hosted MCP server (tools/list). New Webz filters appear automatically, without republishing this package.

Install

pip install llama-index-tools-webz
export WEBZ_API_TOKEN="your-webz-api-token"

Get a token from your Webz.io dashboard (same token as the News Search API).

Full setup and client options: MCP Server docs.

Direct search (no agent required)

from llama_index.tools.webz import WebzNewsSearch, flatten_tool_result

tool = WebzNewsSearch()  # reads WEBZ_API_TOKEN from the environment
# tool = WebzNewsSearch(api_token="your-webz-api-token")

result = tool.call(
    query="recent developments on EU AI regulation",
    k=10,
    days=30,
)
print(flatten_tool_result(result))

To see every filter your connection supports:

print(sorted(WebzNewsSearch().metadata.fn_schema.model_fields))

With a LlamaIndex agent

The agent discovers the live tool schema and picks filters itself. Any tool-calling LLM works (Llama, GPT, Claude, and others). The snippet uses Llama via OpenRouter.

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai_like import OpenAILike
from llama_index.tools.webz import get_webz_tools

tools = get_webz_tools()
# OpenAI-compatible client; any tool-calling LLM works (Llama shown here)
llm = OpenAILike(
    model="meta-llama/llama-3.3-70b-instruct",
    api_key="your-openrouter-key",
    api_base="https://openrouter.ai/api/v1",
    is_chat_model=True,
    is_function_calling_model=True,
)
agent = FunctionAgent(
    tools=tools,
    llm=llm,
    system_prompt="You are a helpful assistant that searches global news with Webz.",
)
response = await agent.run(
    "Search Webz news for renewable energy investments "
    "from the past 30 days and summarize with sources."
)
print(str(response))

Async helpers (when you already run inside an event loop):

from llama_index.tools.webz import aget_webz_tools, awebz_news_search

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

How it works

This package connects to the hosted Webz News Search MCP server at https://news-search-mcp.webz.io/mcp using llama-index-tools-mcp. Each call runs a regular News Search API request with your token (same credits and rate limits). It does not hardcode filter fields - the tool schema comes from the live server.

Configuration

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

Links

• Webz.io
• News Search MCP documentation
• MCP server landing page
• News Search API filters
• LlamaIndex MCP tools
• GitHub