vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MAX_MB | No | Maximum input image size in MB. | 20 |
| VISION_MODELS | No | Comma-separated free models, tried in order (2 attempts each by default). | nvidia/nemotron-3.5-super-vl:free,google/gemma-4-31b-it:free,nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free,google/gemma-4-26b-a4b-it:free |
| VISION_ATTEMPTS | No | Attempts per free model. | 2 |
| VISION_TIMEOUT_MS | No | Per-attempt timeout in milliseconds. | 90000 |
| OPENROUTER_API_KEY | Yes | OpenRouter API key. Read only from the environment — never bundled, never logged. | |
| VISION_ALLOWED_DIR | No | If set, local file reads are confined to this directory (plus OS temp). If unset, the tool can read any local file path. | |
| OPENROUTER_BASE_URL | No | OpenRouter API base URL. | https://openrouter.ai/api/v1 |
| VISION_PAID_ATTEMPTS | No | Attempts for the paid fallback. | 3 |
| VISION_PAID_FALLBACK | No | One cheap paid model tried last as a fallback. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_imageA | Get a text answer about an image using a vision model chain (free OpenRouter models first, then a cheap paid fallback, with retries). Use it when you cannot see the image yourself: UI/design review, OCR, "what is on this screenshot", comparing a render to an expectation. Pass a local file path or an http(s) URL. YOU write the prompt for your task. Returns { content, servedModel, attempts, tried }. |
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 1 tool
Only one tool exists, so there is no possibility of misselection. Its purpose—answering an arbitrary prompt about an image via a vision model chain—is stated unambiguously, including accepted inputs (path or URL) and return shape.
analyze_image follows a clean verb_noun snake_case convention, which is ideal. With a single tool there is no broader pattern to demonstrate consistency against, so it can't quite earn a 5.
A single tool is genuinely sufficient here because the free-form prompt parameter makes it general-purpose (OCR, UI review, render comparison). It is narrowly scoped rather than trivial, though one tool offers no room for specialized conveniences like multi-image diffing.
The domain is 'get an answer about an image,' and the tool covers local paths, URLs, retries, and model fallback with diagnostic metadata returned. Minor gaps: no native multi-image/comparison mode and no way to configure or inspect the model chain, but the prompt-driven design lets agents work around these.