Tools & Automation

Web Search and Fetch

Search the open web and read any URL, with citations.

Two foundational tools every chat has access to. Web Search runs a real search query and returns ranked results. Fetch loads any URL and reads it cleanly. Combined, they let MoClaw answer questions about live information — news, prices, docs, code repos — without leaving the chat.

Try it free All integrations

How it works

3 steps to wire up Web Search and Fetch, no engineering required.

  1. 1

    Ask a question that needs the web

    'What's the latest pricing for AWS RDS?', 'Read this docs page and summarize it', 'What did they announce at the Apple event today?'

  2. 2

    MoClaw runs search and fetch as needed

    It might search to find candidate URLs, fetch a few of them, then synthesize. Citations are inline so you can verify the source of every claim.

  3. 3

    For multi-source investigations, use Deep Research

    Search and Fetch are good for 1 to 3 sources. For 10+ sources or a structured report with cross-checking, Deep Research is the right tool.

Try saying

Real prompts you can paste into Web Search and Fetch.

  • › What's the current price of a 2TB SSD on Amazon, and is it cheaper than 6 months ago?
  • › Read the Anthropic API pricing page and tell me the cached vs uncached input rate for Sonnet 4.6.
  • › Find the GitHub repo for langchain's Postgres vector store and read the README to me.

Step by step demo

What actually happens when you send the prompt.

Prompt 01 3 steps

“Read the Anthropic API pricing page and tell me the cached vs uncached input rate for Sonnet 4.6.”

What MoClaw does

  1. 1 Searches for 'Anthropic API pricing site:anthropic.com'.
  2. 2 Fetches the top result (anthropic.com/pricing) and reads the model table.
  3. 3 Extracts the Sonnet 4.6 row: input $3 per 1M tokens, cached input $0.30 per 1M (90% off).
Result

Replies: 'Sonnet 4.6 is $3 per million input tokens uncached, $0.30 per million when cached — a 90% discount. Cache writes are billed at $3.75 per million (a 25% premium over uncached). Source: anthropic.com/pricing.'

Built for these workflows

Workflows people automate with Web Search and Fetch on MoClaw.

Use case

Amazon Price Tracker

Describe what you want to monitor. MoClaw's AI agent handles the rest.

Use case

AI Agents Research Digest

MoClaw monitors arXiv daily for the latest AI agent papers, summarizes the top findings, and delivers a curated research digest on your schedule.

Use case

Product Hunt Daily Digest

MoClaw fetches the Product Hunt Daily Digest every morning, highlights AI-related projects, and delivers a curated summary with key trends and takeaways.

FAQ

Quick answers about pricing, privacy, and limits.

What search provider do you use?
We rotate between providers (Brave, SerpAPI, Tavily) for resilience and quality. Results are normalized to a single schema before the model sees them.
Can it read sites behind login?
Not Fetch — that uses an unauthenticated HTTP client. For login-gated sites, use Browser Control, which spins up a real Chromium with your saved session.
How fresh is the data?
Search results are real-time. Fetched pages are loaded live, not cached, so what you see is what's currently on the page.
What about paywalled sites?
Fetch reads what the publisher serves; some paywalled sites only return a teaser. We don't bypass paywalls. For research-grade access, point at open-access mirrors or use Deep Research with academic source pinning.

Try MoClaw free.

1,000 credits a month, or bring your own key for unlimited usage.

Start Free Trial

Cancel anytime