browsegrab
by QuartzUnit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROWSEGRAB_LLM_MODEL | No | The specific LLM model to use (e.g., Qwen/Qwen3.5-32B-AWQ). | |
| BROWSEGRAB_LLM_BASE_URL | No | Base URL for the LLM API endpoint (e.g., http://localhost:30000/v1). | |
| BROWSEGRAB_LLM_PROVIDER | No | LLM provider for agentic browse (vllm | ollama | openai). | |
| BROWSEGRAB_AGENT_MAX_STEPS | No | Maximum steps for agentic browsing. Default is 10. | 10 |
| BROWSEGRAB_BROWSER_HEADLESS | No | Whether to run the browser in headless mode. Default is true. | true |
| BROWSEGRAB_AGENT_ENABLE_CACHE | No | Whether to enable domain-based success pattern cache. Default is true. | true |
| BROWSEGRAB_BROWSER_TIMEOUT_MS | No | Browser timeout in milliseconds. Default is 30000. | 30000 |
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