Scrape, crawl, and search the web with Firecrawl in Guild agents

Integrations · Firecrawl

Guild agents use Firecrawl to turn web pages into clean markdown or structured JSON: scrape one page, crawl or map a whole site, search the web and scrape the results, or extract fields with a schema. Guild stores your Firecrawl API key and injects it server-side, so agent code never sees it.

Book a demo

See how teams govern agents that use Firecrawl.

Talk to sales

Get access to Guild, then connect Firecrawl to your first agent.

What the Firecrawl integration exposes

The integration is guildai~firecrawl, and it calls Firecrawl’s v2 API at https://api.firecrawl.dev/v2. Tools cover single and batch scrapes, crawls and their status, site maps, search with scraping, schema-based extraction, Firecrawl’s research agent, browser sessions, and credit and token usage. Crawls, batch scrapes, extractions, and agent runs are asynchronous. The start tool returns a job ID, and the agent polls the matching status tool, such as firecrawl_get_crawl_status, until the job finishes.

How it works

Create a Firecrawl API key

Open API keys in Firecrawl and create a key. It starts with fc-.

Connect the key in Guild

Go to Access & setup > Credentials, click Connect, select firecrawl, and paste the key into API Key.

Import the tools you need

Import FirecrawlTools from @guildai-services/guildai~firecrawl and use pick() to give the agent only the tools its job needs.

Why Firecrawl access needs governing

Every Firecrawl call spends credits, and a crawl can spend many. Guild keeps the key server-side and checks every request against your credential policies, so you can let one agent scrape single pages while denying crawls and agent runs. Give each team its own credential to keep spend attributable.

Authentication

Type: API key
Header: Guild sends the key as Authorization: Bearer <key>

See Credentials for workspace, member, and agent-scoped credentials.

Usage

import { FirecrawlTools } from "@guildai-services/guildai~firecrawl"
import { llmAgent, pick } from "@guildai/agents-sdk"

export default llmAgent({
  systemPrompt: "You read competitor pricing pages and summarize changes.",
  tools: {
    ...pick(FirecrawlTools, [
      "firecrawl_scrape_and_extract_from_url",
      "firecrawl_map_urls",
      "firecrawl_search_and_scrape",
    ]),
  },
})

Tools are named with the firecrawl_ prefix.

Tools

Tools in the latest published version of guildai~firecrawl:

All 32 tools

Tool	What it does
`firecrawl_cancel_agent`	Cancel agent.
`firecrawl_cancel_batch_scrape`	Cancel batch scrape.
`firecrawl_cancel_crawl`	Cancel crawl.
`firecrawl_crawl_params_preview`	Crawl params preview.
`firecrawl_crawl_urls`	Crawl urls.
`firecrawl_create_browser_session`	Create browser session.
`firecrawl_delete_browser_session`	Delete browser session.
`firecrawl_execute_browser_code`	Execute browser code.
`firecrawl_extract_data`	Extract data.
`firecrawl_get_active_crawls`	Get active crawls.
`firecrawl_get_activity`	Lists your team’s recent API activity from the last 24 hours.
`firecrawl_get_agent_status`	Get agent status.
`firecrawl_get_batch_scrape_errors`	Get batch scrape errors.
`firecrawl_get_batch_scrape_status`	Get batch scrape status.
`firecrawl_get_crawl_errors`	Get crawl errors.
`firecrawl_get_crawl_status`	Get crawl status.
`firecrawl_get_credit_usage`	Get credit usage.
`firecrawl_get_extract_status`	Get extract status.
`firecrawl_get_historical_credit_usage`	Get historical credit usage.
`firecrawl_get_historical_token_usage`	Get historical token usage.
`firecrawl_get_queue_status`	Get queue status.
`firecrawl_get_token_usage`	Get token usage.
`firecrawl_interact_with_scrape_browser_session`	Interact with scrape browser session.
`firecrawl_list_browser_sessions`	List browser sessions.
`firecrawl_map_urls`	Map urls.
`firecrawl_scrape_and_extract_from_url`	Scrape and extract from url.
`firecrawl_scrape_and_extract_from_urls`	Scrape and extract from urls.
`firecrawl_search_and_scrape`	Search and scrape.
`firecrawl_start_agent`	Start agent.
`firecrawl_stop_interactive_scrape_browser_session`	Stop interactive scrape browser session.
`firecrawl_support_ask`	Support ask.
`firecrawl_support_docs_search`	Support docs search.

Frequently asked questions

Can a finished Firecrawl crawl trigger a Guild agent?

Not directly. The integration lists crawl and batch_scrape events, but Firecrawl sends its webhooks in its own format, signed with an X-Firecrawl-Signature header. Guild accepts webhooks for this integration only in its own format, so Firecrawl’s deliveries are rejected. Have the agent poll the job’s status tool instead.

How do I keep an agent from running up Firecrawl credits?

Deny the expensive operations, such as firecrawl_crawl_urls and firecrawl_start_agent, in a credential policy, and give the agent firecrawl_get_credit_usage so it can check its balance. See Credential policies.

Does this integration use Firecrawl's v1 API?

No. It calls the v2 API. Firecrawl’s v1 endpoints and the Firecrawl MCP server aren’t part of this integration.

Also runs on Guild: Browserbase · Pinecone Read: Docs: Credential policies · Credentials · Tools in agents

Overview

Models

Inference providers

Code & CI/CD

Communication

Project management

Testing

Design

Productivity

Monitoring & observability

Data

Web & search

Customer support

Sales & finance

Recruiting

Scrape, crawl, and search the web with Firecrawl in Guild agents

Book a demo

Talk to sales

What the Firecrawl integration exposes

How it works

Why Firecrawl access needs governing

Authentication

Usage

Tools

Frequently asked questions

Book a demo

Talk to sales

​What the Firecrawl integration exposes

​How it works

​Why Firecrawl access needs governing

​Authentication

​Usage

​Tools

​Frequently asked questions

​Related

What the Firecrawl integration exposes

How it works

Why Firecrawl access needs governing

Authentication

Usage

Tools

Frequently asked questions

Related