Web Eyes
by slothitude
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_HOST | No | REST API bind address | 0.0.0.0 |
| API_PORT | No | REST API port | 3000 |
| MCP_HOST | No | Standalone MCP bind address | 0.0.0.0 |
| MCP_PORT | No | Standalone MCP port | 3001 |
| NIM_MODEL | No | LLM model for summarization | google/gemma-3-27b-it |
| NIM_API_KEY | Yes | NVIDIA NIM API key (required for summarize/ask) | |
| NIM_BASE_URL | No | NIM API endpoint | https://integrate.api.nvidia.com/v1 |
| SEARXNG_HOST | No | SearXNG host | localhost |
| SEARXNG_PORT | No | SearXNG port | 8888 |
| NIM_VISION_MODEL | No | Vision model for screenshot extraction | google/gemma-3-27b-it |
| VISION_WORD_THRESHOLD | No | Minimum words before triggering vision fallback | 30 |
| VISION_FALLBACK_ENABLED | No | Auto-fallback to vision when text extraction fails | true |
| VISION_MAX_IMAGE_DIMENSION | No | Max screenshot dimension before resize | 1280 |
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 | |