Give your LangChain agent live web search and real-time news

NestDaddy released langchain-nestdaddy, a LangChain integration that adds four tools — NestDaddySearch, NestDaddyNewsSearch, NestDaddyReadPage and NestDaddyNewsRetriever — letting LangChain agents run live web search, real-time news queries with optional country and time-window filters, and full-page article extraction. The package, tested against the live API with LangChain 1.5, installs via pip and uses a single NestDaddy API key that also works for the company's REST API and MCP server, with a free trial available. NestDaddy's guide notes that a system prompt directing the agent to use news search for recent queries and to cite URLs matters, because without it many models never call a tool for time-sensitive questions like 'this week'.

Give your LangChain agent live web search and real-time news Your LangChain agent only knows what its model learned in training. Add three tools from langchain-nestdaddy and it can search the web, read today's news and open full articles. Agent and RAG examples, tested with LangChain 1.5. A LangChain agent is only as current as the model behind it. Ask about something that happened this morning and the model either says it does not know or, worse, guesses with confidence. The fix is to give the agent tools that reach today's internet. This guide uses langchain-nestdaddy https://pypi.org/project/langchain-nestdaddy/ , a LangChain integration for NestDaddy's own search index and real-time news collection, to add: | Class | What it gives the agent | |---|---| | NestDaddySearch | Web search: title, url, snippet and domain of each result | | NestDaddyNewsSearch | Real-time news by key words, with an optional country and time window | | NestDaddyReadPage | The clean main text of any page or article, without menus or ads | | NestDaddyNewsRetriever | News as LangChain Document s for RAG, optionally with the full article text | Everything below was run against the live API with LangChain 1.5. Press Run to call the API. Get your free API key https://nestdaddy.com/mcp Install pip install -U langchain langchain-nestdaddy export NESTDADDY API KEY="your-key" Get a key from the NestDaddy MCP page https://nestdaddy.com/mcp there is a free trial . The same key works for the REST API, the MCP server and this package. Try the tools on their own python from langchain nestdaddy import NestDaddyNewsSearch, NestDaddySearch NestDaddySearch max results=2 .invoke {"query": "model context protocol"} { "query": "model context protocol", "count": 2, "results": {"title": "Roadmap - Model Context Protocol", "url": "https://modelcontextprotocol.io/development/roadmap", "snippet": "Our plans for evolving Model Context Protocol", "domain": "modelcontextprotocol.io", "type": "web"}, {"title": "Model Context Protocol", "url": "https://en.wikipedia.org/wiki/Model Context Protocol", "snippet": "Protocol for communicating between LLMs and applications: The Model Context Protocol MCP is an open standard...", "domain": "en.wikipedia.org", "type": "wiki"} } News works the same way. Keep the query to a few key words, the way a headline would say it: NestDaddyNewsSearch max results=3, days=2 .invoke {"query": "ChatGPT Wallet"} That returned, a few hours after the announcement: 2026-11-13 23:06 cryptobriefing.com OpenAI introduces ChatGPT wallet for Pro subscribers 2026-11-13 23:00 cnbc.com OpenAI launches ChatGPT Wallet, allowing its 'dots' AI agents to make purchases for users 2026-11-13 23:48 investing.com OpenAI launches ChatGPT Wallet, letting AI agents pay for purchases Add "country": "US" or GB, IN, SG, ID and others to limit news to one country. Local news works in the local language, for example {"query": "banjir Jakarta", "country": "ID"} . Give an agent live search and news python from langchain.agents import create agent from langchain nestdaddy import NestDaddyNewsSearch, NestDaddyReadPage, NestDaddySearch agent = create agent "anthropic:claude-sonnet-5-5", tools= NestDaddySearch max results=5 , NestDaddyNewsSearch days=7 , NestDaddyReadPage , system prompt= "Use news search for anything recent, web search for everything else. " "Read a page in full before you explain its details, and cite the urls you used." , result = agent.invoke {"messages": {"role": "user", "content": "What did OpenAI announce this week?"} } print result "messages" -1 .content Any chat model with tool calling works: swap the model string for OpenAI, Gemini, a local model through Ollama, and so on. The system prompt matters more than it looks. Without it, many models never call a tool for "this week" questions, because they do not know their knowledge is out of date. One routing line "news for recent, web for everything else" fixes most of those answers. RAG over today's news When you want documents rather than a tool-calling loop, use the retriever: python from langchain nestdaddy import NestDaddyNewsRetriever retriever = NestDaddyNewsRetriever k=3, days=2, full text=True docs = retriever.invoke "ChatGPT Wallet" for d in docs: print d.metadata "source domain" , d.metadata "full text" , len d.page content cryptobriefing.com True 2611 cnbc.com True 4328 investing.com False 67 With full text=True each article is read in full one extra API call per article . The third article could not be read as clean text, so the retriever kept its summary instead of dropping it: you still get k documents, and metadata "full text" tells you which ones are complete. Feed docs into any LangChain chain or prompt as context. Because every document carries its url and published timestamp , the model can cite sources and say how fresh they are. Async Every tool and the retriever support ainvoke . The retriever reads full articles in parallel: docs = await NestDaddyNewsRetriever k=5, full text=True .ainvoke "AI regulation" Errors you might see API errors raise NestDaddyAPIError with the HTTP status and a hint: a bad key points you to the dashboard, a plan limit to the plans page. The key is stored as a SecretStr , so it never shows up in logs or reprs. Prefer MCP? If you use Claude, Cursor, VS Code or n8n instead of LangChain, the same tools are available as one remote MCP server. Setup for each client is on the NestDaddy MCP page https://nestdaddy.com/mcp . Links - Package: pypi.org/project/langchain-nestdaddy https://pypi.org/project/langchain-nestdaddy/ - Source and tests: github.com/nestdaddy/langchain-nestdaddy https://github.com/nestdaddy/langchain-nestdaddy - REST API reference: nestdaddy.com/apis https://nestdaddy.com/apis