Can I use Firecrawl as a CLI?

Yes. KosmoKrator exposes a Firecrawl CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Firecrawl through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Firecrawl tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Firecrawl credentials stored?

Firecrawl credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Firecrawl MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

data

Firecrawl MCP, CLI, and Lua Integration for AI Agents

Firecrawl integration docs for AI agents: MCP gateway setup, Firecrawl CLI commands, Lua API reference, credentials, and function schemas.

Firecrawl for agents

Credentials can be configured manually in web or CLI hosts.

Use this integration from Lua code mode, the headless integrations CLI, or the KosmoKrator MCP gateway. The same package metadata powers all three surfaces.

Agent Surfaces

Firecrawl CLIHeadless setup, JSON output, direct function calls. Firecrawl MCPExpose selected tools to local MCP clients. Firecrawl LuaAgent-facing namespace and Lua reference. FeedbackReport missing tools, auth issues, or bad metadata.

Machine-Readable Metadata

integration_slug: firecrawl
route_slug: firecrawl
package: firecrawl
auth_strategy: api_key
cli_setup_supported: true
cli_runtime_supported: true
mcp_gateway_supported: true
lua_supported: true

Function Catalog

Function	Type	Parameters	Description
`firecrawl.firecrawl_scrape`	Read `read`	8	Scrape a single URL and extract its content. Returns the page content in the requested format (markdown by default). Supports actions like waiting for JavaScript, taking screenshots, and extracting specific elements.
`firecrawl.firecrawl_search`	Read `read`	10	Search the web with Firecrawl and optionally scrape result pages using scrapeOptions.
`firecrawl.firecrawl_crawl`	Read `read`	9	Start a crawl job to scrape all pages from a website starting at the given URL. Returns a crawl job ID — use firecrawl_get_crawl_status to check progress and retrieve results.
`firecrawl.firecrawl_get_crawl_status`	Read `read`	1	Check the status and retrieve results of a crawl job. Returns the current status (scraping, completed, failed, cancelled) and all scraped data once complete.
`firecrawl.firecrawl_cancel_crawl`	Write `write`	1	Cancel a running Firecrawl crawl job.
`firecrawl.firecrawl_get_crawl_errors`	Read `read`	1	List failed pages and errors for a Firecrawl crawl job.
`firecrawl.firecrawl_get_active_crawls`	Read `read`	0	List currently active Firecrawl crawl jobs for the configured team.
`firecrawl.firecrawl_preview_crawl_params`	Read `read`	2	Preview crawl parameters generated from a natural language crawl prompt.
`firecrawl.firecrawl_map`	Read `read`	7	Map a website to discover all linked URLs. Returns a list of all URLs found on the site without scraping full content. Useful for understanding site structure before crawling.
`firecrawl.firecrawl_batch_scrape`	Read `read`	5	Scrape multiple URLs in one Firecrawl batch job and poll the status with firecrawl_get_batch_scrape_status.
`firecrawl.firecrawl_get_batch_scrape_status`	Read `read`	1	Check Firecrawl batch scrape status and retrieve available results.
`firecrawl.firecrawl_cancel_batch_scrape`	Write `write`	1	Cancel a running Firecrawl batch scrape job.
`firecrawl.firecrawl_get_batch_scrape_errors`	Read `read`	1	List failed URLs and errors for a Firecrawl batch scrape job.
`firecrawl.firecrawl_extract`	Read `read`	7	Extract structured data from one or more URLs using AI. Provide a prompt describing what to extract, or a JSON schema for the expected output format. Ideal for pulling specific data points from web pages.
`firecrawl.firecrawl_get_extract_status`	Read `read`	1	Check status and retrieve results for a Firecrawl extract job.
`firecrawl.firecrawl_agent`	Read `read`	3	Start a Firecrawl agent task for autonomous web navigation and data extraction.
`firecrawl.firecrawl_get_agent_status`	Read `read`	1	Check status and retrieve results for a Firecrawl agent job.
`firecrawl.firecrawl_cancel_agent`	Write `write`	1	Cancel a running Firecrawl agent job.
`firecrawl.firecrawl_create_browser`	Write `write`	2	Create a Firecrawl browser session for interactive web tasks.
`firecrawl.firecrawl_list_browsers`	Read `read`	1	List Firecrawl browser sessions, optionally filtered by status.
`firecrawl.firecrawl_execute_browser`	Write `write`	3	Execute browser automation code or an AI prompt in a Firecrawl browser session.
`firecrawl.firecrawl_delete_browser`	Write `write`	1	Delete or stop a Firecrawl browser session.
`firecrawl.firecrawl_credit_usage`	Read `read`	0	Get remaining Firecrawl credits for the configured team.
`firecrawl.firecrawl_historical_credit_usage`	Read `read`	2	Get historical Firecrawl credit usage for the configured team.
`firecrawl.firecrawl_token_usage`	Read `read`	0	Get remaining Firecrawl extract tokens for the configured team.
`firecrawl.firecrawl_historical_token_usage`	Read `read`	2	Get historical Firecrawl extract token usage for the configured team.
`firecrawl.firecrawl_queue_status`	Read `read`	0	Get Firecrawl scrape queue metrics for the configured team.
`firecrawl.firecrawl_activity`	Read `read`	3	List recent Firecrawl API activity for the configured team.