CAST Imaging

MCP server by CAST

Explore application architecture, transactions, dependencies and quality issues from a CAST Imaging installation through your AI assistant.

Runs locally (Runs on your machine: its page has the install command)Runs with dockerNeeds an API key

Install CAST Imaging

Runs on your machine. Your client starts it with this command:

docker run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4

Needs Docker on your computer. The setup steps below show where the command goes in each client.

  • HOST_CONTROL_PANEL CAST Imaging Control Panel hostname or IP
  • PORT_CONTROL_PANEL optional CAST Imaging Control Panel port
  • SERVICE_HOST Hostname or IP of the machine running the MCP server
  • MCP_SERVER_PORT optional Internal port the MCP server container listens on

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/cast-imaging

About

Connects AI agents to a CAST Imaging installation so they can answer questions about software architecture. Documented use cases include listing applications in a portfolio, exploring architectural graphs, tracing transactions and data flows, browsing database schemas, searching objects with caller and callee relationships, and finding vulnerabilities, cloud readiness blockers and structural flaws.

Runs as a Docker image (castimaging/imaging-mcp-server) on a Linux host with Docker, started through the supplied installer and run.sh script. It must reach the CAST Imaging APIs service and needs a CAST Imaging API key. HOST_CONTROL_PANEL and SERVICE_HOST are required. Source code access is off by default and can be enabled with IMAGING_CODE.

What you can do

  • List applications in a CAST Imaging portfolio with details
  • Explore architectural graphs at different levels
  • Analyze transactions and trace data entity interactions
  • Browse database tables, columns, relationships and constraints
  • Search objects and analyze caller and callee relationships
  • Identify vulnerabilities, cloud readiness blockers and structural flaws

Tools

CAST Imaging lists its tools only to clients with a key, so we can’t show them here.

Example prompts

  • List the applications available in CAST Imaging.

  • Show the main transactions in the billing application.

  • Which database tables does the order service touch?

  • Find cloud readiness blockers in my application.

Set up

Every client starts CAST Imaging on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio cast-imaging --env "HOST_CONTROL_PANEL=<YOUR_HOST_CONTROL_PANEL>" --env "SERVICE_HOST=<YOUR_SERVICE_HOST>" -- docker run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4
  1. Start Claude Code and type /mcp. cast-imaging should show as connected.

Add --scope user to make it available in every project. Replace the placeholders with your own values.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "cast-imaging": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "HOST_CONTROL_PANEL",
        "-e",
        "SERVICE_HOST",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<YOUR_HOST_CONTROL_PANEL>",
        "SERVICE_HOST": "<YOUR_SERVICE_HOST>"
      }
    }
  }
}
  1. Save the file and restart Claude Desktop. Replace the placeholders with your own values.

Needs Docker on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "cast-imaging": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "HOST_CONTROL_PANEL",
        "-e",
        "SERVICE_HOST",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<YOUR_HOST_CONTROL_PANEL>",
        "SERVICE_HOST": "<YOUR_SERVICE_HOST>"
      }
    }
  }
}

Needs Docker on your computer. Replace the placeholders with your own values.

VS Code

Or from a terminal:

code --add-mcp '{"name":"cast-imaging","type":"stdio","command":"docker","args":["run","-e","HOST_CONTROL_PANEL","-e","SERVICE_HOST","-i","--rm","docker.io/castimaging/imaging-mcp-server:3.0.4"],"env":{"HOST_CONTROL_PANEL":"<YOUR_HOST_CONTROL_PANEL>","SERVICE_HOST":"<YOUR_SERVICE_HOST>"}}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "cast-imaging": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-e",
        "HOST_CONTROL_PANEL",
        "-e",
        "SERVICE_HOST",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<YOUR_HOST_CONTROL_PANEL>",
        "SERVICE_HOST": "<YOUR_SERVICE_HOST>"
      }
    }
  }
}

Needs Docker on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "cast-imaging": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "HOST_CONTROL_PANEL",
        "-e",
        "SERVICE_HOST",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<YOUR_HOST_CONTROL_PANEL>",
        "SERVICE_HOST": "<YOUR_SERVICE_HOST>"
      }
    }
  }
}
  1. Refresh the MCP server list in Cascade. Replace the placeholders with your own values.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add cast-imaging --env "HOST_CONTROL_PANEL=<YOUR_HOST_CONTROL_PANEL>" --env "SERVICE_HOST=<YOUR_SERVICE_HOST>" -- docker run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.cast-imaging]
command = "docker"
args = ["run", "-i", "--rm", "docker.io/castimaging/imaging-mcp-server:3.0.4"]
env = { HOST_CONTROL_PANEL = "<YOUR_HOST_CONTROL_PANEL>", SERVICE_HOST = "<YOUR_SERVICE_HOST>" }

Needs Docker on your computer. Replace the placeholders with your own values.

Gemini CLI

gemini mcp add -e "HOST_CONTROL_PANEL=<YOUR_HOST_CONTROL_PANEL>" -e "SERVICE_HOST=<YOUR_SERVICE_HOST>" cast-imaging docker -- run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "cast-imaging": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "HOST_CONTROL_PANEL",
        "-e",
        "SERVICE_HOST",
        "-i",
        "--rm",
        "docker.io/castimaging/imaging-mcp-server:3.0.4"
      ],
      "env": {
        "HOST_CONTROL_PANEL": "<YOUR_HOST_CONTROL_PANEL>",
        "SERVICE_HOST": "<YOUR_SERVICE_HOST>"
      }
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs Docker on your computer. Replace the placeholders with your own values.

Embed

Show CAST Imaging in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![CAST Imaging on mcp.tc](https://mcp.tc/i/cast-imaging/badge.svg)](https://mcp.tc/i/cast-imaging)
HTML
<a href="https://mcp.tc/i/cast-imaging"><img src="https://mcp.tc/i/cast-imaging/badge.svg" alt="CAST Imaging on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/cast-imaging.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/cast-imaging" title="CAST Imaging on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/cast-imaging.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the CAST Imaging card to your site.

Markdown
Add the mcp.tc card for CAST Imaging, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/cast-imaging.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="cast-imaging"><a href="https://mcp.tc/i/cast-imaging">CAST Imaging on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![CAST Imaging on mcp.tc](https://mcp.tc/i/cast-imaging/badge.svg)](https://mcp.tc/i/cast-imaging)
```

Reference: https://mcp.tc/embed

Change history

It runs on your computer and has no package we can follow. Edits by its owner show up here.

Follow CAST Imaging and we’ll email you when something changes.

Nothing recorded yet. Edits by the server’s owner will show up here.

FAQ

Can I paste mcp.tc/i/cast-imaging into my MCP client?

No. CAST Imaging runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is docker run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4.

Does CAST Imaging need an API key?

Yes. CAST Imaging needs an API key from CAST. Keep it in your client’s config on your own machine, never in a shared file.

Is CAST Imaging a remote or a local server?

Local. Your client starts it as a process on your computer with docker run -i --rm docker.io/castimaging/imaging-mcp-server:3.0.4, which needs Docker.

What can CAST Imaging do?

You can list applications in a CAST Imaging portfolio with details, explore architectural graphs at different levels and analyze transactions and trace data entity interactions.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Does mcp.tc track changes to CAST Imaging?

Partly. CAST Imaging runs on your computer and has no package we can follow, so its History tab shows only edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read CAST Imaging’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with CAST. This page was built from CAST Imaging’s public metadata, last checked on 5 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.