Firecrawl MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIRECRAWL_API_KEY | No | Your FireCrawl API key, required when using cloud API (default) | |
| FIRECRAWL_API_URL | No | Custom API endpoint for self-hosted instances (e.g., https://firecrawl.your-domain.com) | |
| FIRECRAWL_RETRY_MAX_DELAY | No | Maximum delay in milliseconds between retries | 10000 |
| FIRECRAWL_RETRY_MAX_ATTEMPTS | No | Maximum number of retry attempts | 3 |
| FIRECRAWL_RETRY_INITIAL_DELAY | No | Initial delay in milliseconds before first retry | 1000 |
| FIRECRAWL_RETRY_BACKOFF_FACTOR | No | Exponential backoff multiplier | 2 |
| FIRECRAWL_CREDIT_WARNING_THRESHOLD | No | Credit usage warning threshold | 1000 |
| FIRECRAWL_CREDIT_CRITICAL_THRESHOLD | No | Credit usage critical threshold | 100 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| firecrawl_scrapeC | Scrape a single webpage with advanced options for content extraction. Supports various formats including markdown, HTML, and screenshots. Can execute custom actions like clicking or scrolling before scraping. |
| firecrawl_mapC | Discover URLs from a starting point. Can use both sitemap.xml and HTML link discovery. |
| firecrawl_crawlB | Start an asynchronous crawl of multiple pages from a starting URL. Supports depth control, path filtering, and webhook notifications. |
| firecrawl_batch_scrapeC | Scrape multiple URLs in batch mode. Returns a job ID that can be used to check status. |
| firecrawl_check_batch_statusB | Check the status of a batch scraping job. |
| firecrawl_check_crawl_statusB | Check the status of a crawl job. |
| firecrawl_searchA | Search and retrieve content from web pages with optional scraping. Returns SERP results by default (url, title, description) or full page content when scrapeOptions are provided. |
| firecrawl_extractC | Extract structured information from web pages using LLM. Supports both cloud AI and self-hosted LLM extraction. |
| firecrawl_deep_researchC | Conduct deep research on a query using web crawling, search, and AI analysis. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have distinct purposes, but there is some potential overlap between firecrawl_scrape and firecrawl_extract, as both involve extracting content from web pages. The descriptions clarify that scrape focuses on raw content extraction with advanced options, while extract uses LLM for structured information, but an agent might still confuse them. Other tools like crawl, map, search, and deep_research are clearly differentiated.
All tool names follow a consistent 'firecrawl_' prefix with snake_case and descriptive verb_noun patterns (e.g., batch_scrape, check_batch_status, crawl, deep_research). This uniformity makes the set predictable and easy to navigate, with no deviations in naming conventions across the nine tools.
With 9 tools, the count is well-scoped for a web crawling and scraping server, covering key operations like single and batch scraping, crawling, mapping, searching, and deep research. Each tool serves a specific function without redundancy, making the set comprehensive yet manageable for typical use cases.
The tool set covers the core web crawling and scraping domain effectively, including initiation, status checking, and various extraction methods. A minor gap exists in the lack of tools for managing or deleting jobs, but agents can work around this by relying on job IDs and status checks. Overall, the surface supports essential workflows without significant dead ends.