image_analysisLABSCO SUMMARY
One tool, and the query is where the quality comes from.
The README is blunt about the difference: "Describe this image" returns far less than "Identify all retail products visible in this store shelf image and estimate their price range". Because the model is a per-call parameter, routine images can go to the free default and only the ones that matter need a stronger model.
What it is
A Python server with a single tool, image_analysis, that sends an image and your question to a vision model on OpenRouter and returns the model's answer.
What you get
image_analysisaccepts the image three ways: base64 data, an http/https URL, or a path to a file on disk- A
queryyou write yourself, so the answer is scoped to what you need rather than a generic description - An optional
system_promptto give the model a role, plustemperatureandmax_tokens - A
modelparameter per call — any OpenRouter model with vision support,openai/gpt-4oandanthropic/claude-3-5-sonnetamong them - A
project_rootparameter so relative image paths resolve against a directory you name, not the server's working directory
Requirements
OPENROUTER_API_KEY is required. OPENROUTER_DEFAULT_MODEL is optional and falls back to qwen/qwen2.5-vl-32b-instruct:free. Install with pip install mcp-openvision or uv pip install mcp-openvision, and launch with uvx mcp-openvision.
Setup effort
One command plus a key — pip install mcp-openvision, then supply credentials
USE CASES
01
Getting numbers out of a chart someone sent you
Point at the image and ask for the values and the trend, rather than a description of the picture.
02
Transcribing text from a photo
Ask for a transcription that preserves structure — item names, descriptions and prices stay together instead of collapsing into a paragraph.
03
Reviewing a design or a screenshot on your own disk
Pass a local file path, or a relative path plus project_root when the server's working directory isn't predictable.
04
Running a specialist read on one image
Set system_prompt to the expertise you need and raise max_tokens when you want the long answer.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- uvx on PATH
- OPENROUTER_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install mcp-openvisionMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"openvision": {
"command": "uvx",
"args": [
"mcp-openvision"
],
"env": {
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"OPENROUTER_DEFAULT_MODEL": "anthropic/claude-3-sonnet"
}
}
}
}
