MCP Firecrawl
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_HOST | No | HTTP bind address (HTTP mode only) | 127.0.0.1 |
| HTTP_PORT | No | HTTP port (HTTP mode only) | 3001 |
| FIRECRAWL_API_KEY | Yes | Your Firecrawl API key |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scrape_urlA | Scrape a single webpage and return clean markdown content with metadata |
| crawl_websiteA | Crawl multiple pages from a website and return extracted markdown content |
| search_webB | Search the web using Firecrawl and return relevant results with content summaries |
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 3 tools
Each tool targets a distinct action: crawling multiple pages, scraping a single page, and searching the web. There is no overlap in purpose.
All tool names follow a consistent verb_noun pattern using snake_case: crawl_website, scrape_url, search_web.
3 tools is slightly lean but covers the core web extraction tasks. More tools could be added (e.g., for authentication), but the set is scoped appropriately.
The tools cover the primary operations: crawling, scraping, and searching. Minor gaps exist (e.g., no tool for custom headers), but the surface is functional for typical use cases.