Firecrawl integration for AI agents.
Firecrawl integration for AI agents with secure authentication and server-side credential injection. Open Connector runs the OAuth, seals the token in an encrypted vault, and serves Firecrawl tools to your agent over MCP or a typed API — credentials injected server-side, every call audited, nothing leaving your infrastructure. Open source (AGPL-3.0) and self-hostable.
Real Firecrawl actions, managed and audited.
Your user connects Firecrawl once; your agent can then firecrawl is the context API to search, scrape, and interact with the web at scale. Turn any source into clean Markdown or structured data your agents can ship with — scoped to the OAuth permissions you grant and the tool allowlist you configure. Every action is least-privilege and written to a tamper-evident audit trail.
- 1
Your user grants Firecrawl access once (OAuth) — the token lands in the vault.
- 2
Your agent calls a tool over MCP or the typed API; Open Connector injects the credential server-side.
- 3
Every routed call appends a hash-chained audit record — nothing leaves your infra.
Supported Firecrawl tools.
18 tools are generated from the published Firecrawl catalog. Descriptions are plain text; each action remains subject to its configured authentication and tool allowlist.
Showing 18 tools. All published catalog entries are included in this page's server-rendered HTML.
- Cancel a batch scrape job
- Cancel a batch scrape job
- Scraping
- Cancel a crawl job
- Cancel a crawl job
- Crawling
- Crawl multiple URLs based on options
- Crawl multiple URLs based on options
- Crawling
- Extract structured data from pages using LLMs
- Extract structured data from pages using LLMs
- Extraction
- Get all active crawls for the authenticated team
- Get all active crawls for the authenticated team
- Crawling
- Get the errors of a batch scrape job
- Get the errors of a batch scrape job
- Scraping
- Get the status of a batch scrape job
- Get the status of a batch scrape job
- Scraping
- Get the errors of a crawl job
- Get the errors of a crawl job
- Crawling
- Get the status of a crawl job
- Get the status of a crawl job
- Crawling
- Get remaining credits for the authenticated team
- Get remaining credits for the authenticated team
- Billing
- Get the status of an extract job
- Get the status of an extract job
- Extraction
- Get historical credit usage for the authenticated team
- Get historical credit usage for the authenticated team
- Billing
- Get historical token usage for the authenticated team (Extract only)
- Get historical token usage for the authenticated team (Extract only)
- Billing
- Get remaining tokens for the authenticated team (Extract only)
- Get remaining tokens for the authenticated team (Extract only)
- Billing
- Map multiple URLs based on options
- Map multiple URLs based on options
- Mapping
- Scrape a single URL and optionally extract information using an LLM
- Scrape a single URL and optionally extract information using an LLM
- Scraping
- Scrape multiple URLs and optionally extract information using an LLM
- Scrape multiple URLs and optionally extract information using an LLM
- Scraping
- Search and optionally scrape search results
- Search and optionally scrape search results
- Search
Firecrawl integration, answered
- How do AI agents use Firecrawl through Open Connector?
- Your user connects Firecrawl once with one of its cataloged authentication methods. Open Connector stores the credential in an encrypted vault and exposes Firecrawl tools to your agent over MCP or a typed API, with credentials injected server-side on each call.
- Is this a Firecrawl MCP server?
- Yes. Open Connector can serve Firecrawl as a named MCP server with a scoped allowlist and a per-user connection URL, so any MCP client can call Firecrawl actions with credentials injected server-side.
- Where do Firecrawl credentials live?
- In your own infrastructure. Open Connector keeps credentials in its own vault and injects them at call time, so they never leave your environment.
Give your agents Firecrawl — keep the keys.
Open source, self-hostable, with Firecrawl credentials that never leave your infrastructure. Run it from source today.