ollama-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_INBOX | No | Alias for VISION_MCP_INBOX | |
| VISION_MODEL | No | Alias for VISION_MCP_MODEL | |
| VISION_API_KEY | No | Alias for VISION_MCP_API_KEY | |
| VISION_BASE_URL | No | Alias for VISION_MCP_BASE_URL | |
| VISION_MCP_INBOX | No | Default folder for list_images | .agents/inbox |
| VISION_MCP_MODEL | No | Vision model to use | qwen2.5vl:7b |
| VISION_MCP_API_KEY | No | API key (Ollama ignores it) | |
| VISION_MCP_BASE_URL | No | OpenAI-compatible base URL (Ollama) | http://localhost:11434/v1 |
| VISION_MCP_COMPRESS | No | Auto-downscale images > 50 KB to 768px JPEG | 1 |
| VISION_MCP_MAX_TOKENS | No | Max output tokens for the vision model | 2048 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_imageA | Read a local image and return a text description from the local Ollama vision model. Use when the user references a screenshot or image you cannot see.
|
| list_imagesA | List image files in a directory. Defaults to the configured inbox folder where the user drops screenshots. Use this before describe_image to find what is available. |
| extract_textA | Extract all visible text (OCR) from a local image verbatim. Use for code screenshots, terminal output, or error dialogs. |
| vision_statusA | Show bridge configuration and Ollama connectivity / available models. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clear, distinct purpose: list_images finds images, describe_image provides semantic description, extract_text performs OCR, and vision_status checks configuration. There is no overlap or ambiguity between them.
Tool names predominantly follow a verb_noun snake_case pattern (describe_image, list_images, extract_text). The exception is vision_status, which is noun_noun rather than verb_noun, but the inconsistency is minor and the naming style remains uniform.
With 4 tools, the server is well-scoped for a focused vision MCP. Each tool serves a necessary role in the image-analysis workflow, and the count is neither too sparse nor excessive.
The tool surface covers the core workflows: discovering available images, getting a semantic description, extracting text, and verifying connectivity. There are no obvious gaps that would prevent an agent from completing typical vision-related tasks.