RouterGrowth

Find and enrich12 capabilities

Companies, the people in them, verified emails and buying signals

Research the market21 capabilities

Search, social networks, ad libraries, reviews and AI answers

Reach out and create43 capabilities

Sending domains, inboxes, LinkedIn and the creative that goes out

3,000+ tools behind 76 capabilities, one key, one prepaid balance All tools →Catalog →Free tools →

Find leads48 workflows

Lists built from hiring, funding, the tech stack and Google Maps

Run outbound37 workflows

Cold email, LinkedIn and follow-ups, from the first list to the reply

Watch the market43 workflows

SEO, AI answers, competitors' ads, brand mentions and ad creative

99 workflows with the prompt to paste, 18 guides, 11 skills your agent installs All workflows →Guides →Skills →

Pricing Docs Get started

Tools / Job

Web search and scraping for your AI agent: find the page, read it, pull the records

Q: Is this a Firecrawl MCP?

Firecrawl is one of the providers behind web.scrape, web.search and web.extract, alongside Apify. You use one key and the router handles failover.

RouterGrowth gives an agent the open web through one MCP server: a search that returns sources it can cite, any URL as clean markdown, and structured records pulled from a page against a template. Firecrawl and Apify sit behind the same call, with failover between them.

4 tools live 3 providers from $0.004 a call MCP · REST · CLI

Ask your agent

Read the pricing pages of these 12 competitors and put the plans in one table.

Add to Claude Add to ChatGPT

Connect RouterGrowth once, then ask in plain words. New workspaces start with $1 of credit. Get a key or read the setup guide.

Web search and scraping tools

What can your agent do for web search and scraping?

Each row is one tool your agent can call. The price is the lowest a successful call costs at list price. The exact figure is quoted before every run.

Tool	What it returns	Providers	From
Agent web searchweb.search	Semantic or keyword web search returning sources an agent can cite.	DataForSEOFirecrawlApify	$0.004per search
Website scrapeweb.scrape	Clean markdown of a page or site for agent context.	FirecrawlApify	$0.006per page
Page to recordsweb.extract	One page in, dated records out: a leadership page, an official bio, an org chart, a press release or a job listing extracted against a template (or your own JSON schema), each record with the sentence on the page that supports it, the page date and the source URL. Watch-friendly: records key on the person or posting, so a weekly refresh reports who joined, left or changed title.	Firecrawl	$0.028per page
News searchnews.search	Google News articles for a query and location: title, source, snippet, URL and publication time.	DataForSEOFirecrawl	$0.004per search

Every tool has a page with its input schema, its output fields and the price on each provider. Browse the whole catalog or see how plans lower every price.

In practice

What do you ask it?

You do not call tools by name. You describe the job, and the agent finds the tools, shows the price and runs them.

Read the pricing pages of these 12 competitors and put the plans in one table.

web.scrape

Search the web for independent reviews of this product and summarise them with links.

web.search web.scrape

Pull the leadership team from each of these company pages: name, title and the sentence that says so.

web.extract

Connect

How do you connect it?

One MCP server for Claude, ChatGPT, Claude Code, Codex and Cursor, or the same calls over the CLI and REST. The example runs web.search.

MCP server

claude mcp add --transport http routergrowth https://api.routergrowth.com/mcp

CLI

npm install -g routergrowth && routergrowth setup
routergrowth run -c web.search -i '{"query": "independent reviews of Notion", "limit": 10}'

REST

curl -X POST https://api.routergrowth.com/v1/run \
  -H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
  -d '{"capability": "web.search", "input": {"query": "independent reviews of Notion", "limit": 10}}'

In claude.ai and ChatGPT, add https://api.routergrowth.com/mcp as a connector and approve the workspace in the browser. Setup for every client.

Worth knowing

What should you know before you start?

Two providers, one call

When one scraper fails on a page, the router tries the other. Only the one that returns the page is charged.

Records with evidence

web.extract returns each record with the sentence on the page that supports it and the page date, so the agent can check its own work.

Markdown, not HTML

Pages come back as clean markdown sized for a model's context.

FAQ

Questions about web search and scraping with an AI agent

Is there a web search MCP server?

RouterGrowth is an MCP server with web search, page scraping, structured extraction and news search as tools.

Is this a Firecrawl MCP?

Firecrawl is one of the providers behind web.scrape, web.search and web.extract, alongside Apify. You use one key and the router handles failover.

Can it scrape any website?

It reads public pages and returns markdown. Pages behind a login are out of scope, and some sites block automated readers: when both providers fail, nothing is charged.

How is web.extract different from scraping?

Scraping returns the page. Extraction returns records from it against a template or your own schema, each with its supporting sentence.