CAST Imaging MCP Server

Overview

CAST Imaging MCP Server is a Model Context Protocol (MCP) server: MCP server exposing CAST Imaging software architecture insights to AI agents. In practice that means any MCP-compatible AI assistant can call CAST Imaging MCP Server's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Docker image docker.io/castimaging/imaging-mcp-server:3.0.4 speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need HOST_CONTROL_PANEL, SERVICE_HOST. The current release is v3.0.4, with source at CAST-Extend/CAST-Imaging-Mcp on GitHub.

CAST Imaging MCP Server is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain CAST Imaging MCP Server for CAST-Extend, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "cast_imaging_mcp_server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<host-control-panel>",
        "SERVICE_HOST": "<service-host>"
      }
    }
  }
}

Requires HOST_CONTROL_PANEL, SERVICE_HOST