Vision MCP
Enables any MCP client to perform image understanding and OCR via any OpenAI-compatible vision-language model. Supports local, private inference without images leaving the machine.
AI & Machine Learning
npm 0 platforms
0 features
Install
npx -y vision-mcp
Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.
{
"mcpServers": {
"vision-mcp": {
"command": "npx",
"args": [
"-y",
"vision-mcp"
],
"env": {
"VLM_MODEL": "<VLM_MODEL>",
"VLM_API_MODE": "<VLM_API_MODE>",
"VLM_BASE_URL": "<VLM_BASE_URL>",
"VLM_KEEP_ALIVE": "<VLM_KEEP_ALIVE>",
"VLM_TIMEOUT_MS": "<VLM_TIMEOUT_MS>"
}
}
}
}Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.
Sources: public MCP Server directories. This is an independent third-party directory with no affiliation to or endorsement from the maintainers of the listed servers.
