Teach your AI agents to See, Act and Automate – with VLM Run MCP
Capability Showcase
Capability Showcase
Face Detection / Blur
Face Detection / Blur
Document Redaction
Document Redaction
Visual Search
Visual Search
Video Editing
Video Editing
Get your API key
$VLMRUN_API_KEY
). We’ll use this to authenticate your requests to the MCP server next.Add the server to your MCP client
$VLMRUN_API_KEY
. In the request header, this will be the value of the Authorization
header.Ping the MCP server to test
Start building your agent with VLM Run MCP
Configure your MCP client
https://mcp.vlm.run/mcp/sse
to your MCP client configuration with Bearer token authentication. Works with Claude Desktop, OpenAI API, Gemini SDK, or any MCP-compatible platform.Agent discovers available tools
parse_image
, parse_document
, put_image_url
, put_file_url
, and so on.Natural conversation triggers tools
Get actionable results