An MCP server that provides image recognition to text-only LLMs via an OpenAI-compatible multimodal endpoint.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"simple-vision-mcp": {
"command": "cargo",
"args": [
"run",
"--",
"simple-vision-mcp"
]
}
}
}
Run in terminal:
claude mcp add simple-vision-mcp cargo run -- simple-vision-mcp
Add to .cursor/mcp.json:
{
"mcpServers": {
"simple-vision-mcp": {
"command": "cargo",
"args": [
"run",
"--",
"simple-vision-mcp"
]
}
}
}