firecrawl-lite-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | Yes | Model name to use for extraction (e.g., gpt-5.5). | |
| LLM_TOP_P | No | Nucleus sampling; omitted unless set. | |
| LLM_API_KEY | Yes | API key for your LLM provider. | |
| PROXY_LLM_API | No | Set to 'true' to also proxy LLM API calls through the upstream proxy. | |
| LLM_MAX_TOKENS | No | Maximum tokens in the response. | 2000 |
| LLM_TEMPERATURE | No | Sampling temperature. | 0.1 |
| PROXY_SERVER_URL | No | Upstream proxy URL for scraping browser (e.g., http://proxy.example.com:10001-10010). | |
| SCRAPE_DELAY_MAX | No | Maximum delay before navigation in ms. | 3000 |
| SCRAPE_DELAY_MIN | No | Minimum delay before navigation in ms. | 1000 |
| SCRAPE_USER_AGENT | No | User agent string or JSON array of strings to rotate. | |
| ENABLE_SSE_ENDPOINT | No | Enables SSE endpoint on /sse. Default is false. | |
| LLM_REASONING_EFFORT | No | reasoning_effort for reasoning-capable models; omitted unless set. | |
| SCRAPE_SETTLE_MAX_MS | No | Maximum wait for DOM to settle after load in ms. | 3000 |
| LLM_PROVIDER_BASE_URL | Yes | Base URL of an OpenAI-compatible API (e.g., https://api.openai.com/v1). | |
| PROXY_SERVER_PASSWORD | No | Password for proxy authentication. | |
| PROXY_SERVER_USERNAME | No | Username for proxy authentication. | |
| SCRAPE_VIEWPORT_WIDTH | No | Viewport width in pixels. | |
| SCRAPE_BATCH_DELAY_MAX | No | Maximum delay between batch requests in ms. | 5000 |
| SCRAPE_BATCH_DELAY_MIN | No | Minimum delay between batch requests in ms. | 2000 |
| SCRAPE_VIEWPORT_HEIGHT | No | Viewport height in pixels. | |
| FIRECRAWL_RETRY_MAX_DELAY | No | Maximum retry delay in ms. | 10000 |
| FIRECRAWL_RETRY_MAX_ATTEMPTS | No | Maximum number of retry attempts. | 3 |
| FIRECRAWL_RETRY_INITIAL_DELAY | No | Initial retry delay in ms. | 1000 |
| FIRECRAWL_RETRY_BACKOFF_FACTOR | No | Retry backoff factor. | 2 |
| ENABLE_HTTP_STREAMABLE_ENDPOINT | No | Enables HTTP Streamable endpoint on /mcp. Default is false. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scrape_pageA | Extract content from a single webpage |
| batch_scrapeA | Scrape multiple URLs in a single request |
| extract_dataB | Extract structured data from webpages using LLM |
| extract_with_schemaC | Extract structured data using a JSON schema |
| screenshotB | Take a screenshot of a webpage using stealth browser |
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 5 tools
Most tools have clearly distinct purposes: scraping, batch scraping, LLM extraction, schema-based extraction, and screenshots. The only potential confusion is between extract_data and extract_with_schema, but their descriptions make the distinction clear.
All names use lowercase with underscores and mostly follow a verb-first pattern (scrape_page, batch_scrape, extract_data, extract_with_schema). 'screenshot' breaks the verb_noun pattern but is still a familiar, predictable command.
Five tools is well-scoped for a 'lite' server: it covers single scraping, batch scraping, two flavors of structured extraction, and screenshots. Each tool earns its place without redundancy or bloat.
The core web data collection lifecycle is covered: raw content extraction, batch processing, structured extraction, and visual capture. Missing crawls or search features, but those are likely intentionally excluded from a lite server.