{"slug": "build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http", "title": "Build an n8n AI agent that knows today's news (MCP or plain HTTP)", "summary": "A step-by-step guide published on NestDaddy's site shows how to give n8n's AI Agent node access to current news through two methods: connecting an MCP server at https://mcp.nestdaddy.com/mcp via the MCP Client Tool node with HTTP Streamable transport and Bearer Auth, or calling the NestDaddy news API (https://nestdaddy.com/api/v1/news/search) from an HTTP Request node in a scheduled workflow. The guide uses NestDaddy, an independent search engine with its own web index and news collection, and notes a free 7-day key with 5,000 calls and no card requirement is enough to build and test both setups. The MCP approach lets the agent choose which tools to call — including news_search, country_news and read_page — while the pipeline approach runs a daily 07:00 Schedule Trigger, queries with parameters such as q=OpenAI, days=1, limit=15 and country=GB, then has an LLM summarize results into Slack, Telegram or email.", "body_md": "# Build an n8n AI agent that knows today's news (MCP or plain HTTP)\n\nn8n's AI Agent only knows what its model learned in training. Two ways to fix it: connect an MCP server so the agent searches the web and news by itself, or call a news API from an HTTP Request node in a scheduled workflow. Step by step, no code.\n\nn8n's **AI Agent** node is great at reasoning over what you give it. Ask it about something that happened this morning, though, and it can only guess: the model behind it stopped learning months ago.\n\nThis guide shows two ways to give an n8n workflow live news and web search:\n\n1. **Agent mode:** connect an MCP server to the AI Agent node. The agent decides when to search the news, search the web or read an article in full. Best for chat-style workflows and research tasks.\n2. **Pipeline mode:** a scheduled workflow calls a news API with the**HTTP Request** node, then an LLM summarises the results and sends them to Slack, Telegram or email. Best for daily briefs and keyword alerts.\n\nBoth use the same API key. The examples use [NestDaddy](https://nestdaddy.com/mcp), an independent search engine with its own web index and news collection. A free 7-day key (5,000 calls, no card) is enough to build and test both.\n\n## Option 1: AI Agent + MCP Client Tool\n\n### What you build\n\n``` php\nChat Trigger  ->  AI Agent  (model: any chat model you use in n8n)\n                     |-- MCP Client Tool  ->  NestDaddy (news, web search, read page...)\n```\n\n### Steps\n\n1. Add a **Chat Trigger** node (or any trigger that passes a question).\n2. Add an **AI Agent** node and connect your chat model (OpenAI, Anthropic, Gemini, Ollama or any model you already use in n8n).\n3. On the agent's **Tool** input, add an**MCP Client Tool** node:\n   -**Endpoint:**`https://mcp.nestdaddy.com/mcp` -** Server Transport:** HTTP Streamable\n   -**Authentication:** Bearer Auth, with a credential that holds your key (or Header Auth with`Authorization: Bearer YOUR_KEY` )\n4. Leave \"Tools to include\" on all tools, or pick the ones you need (for a news assistant: `news_search` ,`country_news` ,`read_page` ).\n5. In the agent's system message, tell it when to use the tools:\n\n```\nYou answer questions about current events. Always use news_search for anything\nthat may have happened recently, and read_page to read the one or two most\nrelevant articles in full before answering. Mention the date of each fact and\nlist the article URLs you used.\n```\n\nOpen the chat and ask something like *\"What changed in EU AI rules this week?\"*. In the execution log you will see the agent call `news_search`, then `read_page`, then answer with sources.\n\n### Why MCP instead of hard-coded HTTP calls\n\n- The agent chooses **which** tool to call and**what** to search for, based on the question.\n- One node gives the agent several tools: news by key words, country news, web search, page reading and research papers.\n- The same server works in Claude, Cursor and VS Code, so you test prompts once and reuse them everywhere ([Claude setup](https://nestdaddy.com/blog/add-live-web-search-to-claude-mcp) ,[Cursor setup](https://nestdaddy.com/blog/cursor-web-search-mcp) ).\n\n## Option 2: scheduled news brief with HTTP Request\n\n### What you build\n\n``` php\nSchedule Trigger (every morning)\n   -> HTTP Request   (news search for your topics)\n   -> AI Agent / LLM (summarise into a short brief)\n   -> Slack / Telegram / Send Email\n```\n\n### Steps\n\n1. **Schedule Trigger:** every day at 07:00 in your time zone.\n2. **HTTP Request** node:\n   -**Method:** GET\n   -**URL:**`https://nestdaddy.com/api/v1/news/search` -** Authentication:** Generic Credential Type → Header Auth, with header name`X-API-Key` and your key as the value\n   -**Query parameters:**\n\n| Name | Value | Notes | \n|---|---|---|\n| `q` | `OpenAI` | Your topic, as key words | \n| `days` | `1` | Only the last day | \n| `limit` | `15` | Enough for a brief | \n| `country` | `GB` | Optional: only news from one country (two-letter code) | \n\nThe response has a `results` list; each item has `title`, `url`, `source_domain`, `published_timestamp` and `description`.\n3. **AI Agent** (or a plain LLM node) with a prompt like:\n\n```\nHere are today's news results as JSON: {{ JSON.stringify($json.results) }}\nWrite a brief for a busy reader: at most 6 bullet points, each one sentence,\nmerge duplicates of the same story, and end each bullet with the source link.\n```\n\n1. **Slack** ,**Telegram** or**Send Email** node: send the agent's output.\n\nSeveral topics? Put a small list in a **Code** node before the HTTP Request (one item per topic); n8n runs the request once per item, and a **Merge** or **Aggregate** node collects them again before the summary.\n\n### Keyword alerts instead of a daily brief\n\nChange the schedule to every 30 or 60 minutes, set `days` to `1`, and add an **IF** node that only continues when `results` is not empty. To avoid sending the same story twice, keep the URLs you already sent (n8n's workflow static data in a Code node, or a small table in your database) and filter them out.\n\n## Which option should you use?\n\n| You want | Use | \n|---|---|\n| A chat assistant that answers questions about current events | Option 1 (MCP) | \n| A research step inside a bigger agent workflow | Option 1 (MCP) | \n| A fixed daily or hourly brief | Option 2 (HTTP Request) | \n| Alerts when a company, product or person appears in the news | Option 2 with an IF node | \n\nMany workflows use both: a scheduled brief for the team, and an agent for follow-up questions.\n\n## Costs and limits\n\nEvery MCP tool call or HTTP request counts as one call; connecting the MCP server and listing tools is free. A daily brief over three topics uses about 90 calls a month, and an agent that reads two articles per question uses three or four calls per question. Plans start at $9.99 a month for 10,000 calls after the free 7-day trial: [get a key](https://nestdaddy.com/apis).\n\nPrefer code over nodes? The same daily brief in Python, with dedupe and Telegram, Slack or email delivery: [Build a daily news digest bot in Python](https://nestdaddy.com/blog/news-digest-bot-python).", "url": "https://wpnews.pro/news/build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http", "canonical_source": "https://nestdaddy.com/blog/n8n-ai-agent-live-news", "published_at": "2026-11-13 00:00:00+00:00", "updated_at": "2026-11-13 16:52:10.604300+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "agent-protocols", "ai-search"], "entities": ["n8n", "NestDaddy", "MCP Client Tool", "AI Agent", "HTTP Request", "OpenAI", "Anthropic", "Slack"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http", "markdown": "https://wpnews.pro/news/build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http.md", "text": "https://wpnews.pro/news/build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http.txt", "jsonld": "https://wpnews.pro/news/build-an-n8n-ai-agent-that-knows-today-s-news-mcp-or-plain-http.jsonld"}}