local-vision-mcp
by tmchao7
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Debug logging level (e.g., debug) | |
| VISION_MODEL | No | Ollama vision model | qwen3-vl:4b |
| VISION_MAX_BYTES | No | Image size limit (20 MiB) | 20971520 |
| VISION_KEEP_ALIVE | No | Ollama model keep-alive | 5m |
| VISION_TIMEOUT_MS | No | Total request budget across both attempts | 90000 |
| CLAUDE_PROJECT_DIR | No | Claude project directory, falls back to cwd | |
| VISION_OLLAMA_HOST | No | Ollama endpoint | http://127.0.0.1:11434 |
| VISION_ALLOWED_PATHS | No | Extra allowed image directories, ':'-separated | |
| VISION_MAX_OUTPUT_CHARS | No | Report text cap | 12000 |
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