uspto-crawler-mcp
by YobieBen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port | 3001 |
| LLM_MODEL | No | LLM model name | gpt-4 |
| LOG_LEVEL | No | Log level (debug, info, warning, error) | info |
| LLM_PROVIDER | No | LLM provider (openai, etc.) | openai |
| USE_SELENIUM | No | Enable Selenium-based scraping (true/false) | false |
| OPENAI_API_KEY | No | Optional OpenAI API key for LLM extraction | |
| CRAWL4AI_TIMEOUT | No | Timeout for Crawl4AI requests in milliseconds | 30000 |
| SELENIUM_BROWSER | No | Browser to use (chrome/firefox) | chrome |
| CRAWL4AI_HEADLESS | No | Run Crawl4AI in headless mode (true/false) | true |
| SELENIUM_HEADLESS | No | Run browser in headless mode (true/false) | false |
| CRAWL4AI_USER_AGENT | No | User agent string for Crawl4AI | USPTO-Crawler/0.2 |
| MAX_CONCURRENT_CRAWLS | No | Maximum number of concurrent crawls | 5 |
| DELAY_BETWEEN_REQUESTS | No | Delay between requests in milliseconds | 1000 |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues