OpenSight MCP
by Mr-JoE1
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OCR_MODEL | No | Default OCR model | minicpm-v:latest |
| MAX_TOKENS | No | Max response tokens | 2048 |
| OLLAMA_HOST | No | Ollama server host:port | 192.168.46.34 |
| OLLAMA_PORT | No | Ollama API port | 11434 |
| VISION_MODEL | No | Default vision model | minicpm-v:latest |
| GOOGLE_API_KEY | No | Google Gemini API key | |
| OPENAI_API_KEY | No | OpenAI API key | |
| VISION_PROVIDER | No | Backend: ollama, openai, google, openrouter | ollama |
| VISION_KEEP_ALIVE | No | Model keep-alive duration | 10m |
| VISION_TIMEOUT_MS | No | Request timeout (ms) | 120000 |
| OPENROUTER_API_KEY | No | OpenRouter API key | |
| VISION_MAX_RETRIES | No | Retry attempts on failure | 3 |
| VISION_WARMUP_ON_START | No | Auto-warmup model on server start | 1 |
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
ActivitySlowing
ResponsivenessNo issues