About Image Builder MCP
Image Builder MCP is a draft MCP server for interacting with hosted image builder. It is intended for AI/LLM clients and supports SSE and stdio operation modes.
Key features
- 01Connects to hosted image builder
- 02SSE and stdio modes
- 03Service-account credentials
Use cases
- 01Connect an AI client to hosted image builder
- 02Run the server locally in SSE or stdio mode
MCP support
The MCP server exposes interactions with hosted image builder to MCP clients. It can run over SSE or stdio.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEImage Builder MCP
This repo is in a DRAFT and playground state!
An MCP server to interact with hosted image builder
Authentication
Go to https://console.redhat.com to 'YOUR USER' ➡ My User Access ➡ Service Accounts create a service account
and then set the environment variables IMAGE_BUILDER_CLIENT_ID and IMAGE_BUILDER_CLIENT_SECRET accordingly.
Run
Using Python directly
Install the package in development mode:
pip install -e .
Then run using either:
python -m image_builder_mcp sse
or using the CLI entry point:
image-builder-mcp sse
This will start image-builder-mcp server at http://localhost:9000/sse
Using Podman/Docker
You can also copy the command from the [Makefile] For SSE mode:
make run-sse
You can also copy the command from the [Makefile] For stdio mode:
make run-stdio
Integrations
VSCode
For the usage in your project, create a file called .vscode/mcp.json with
the following content.
{
"inputs": [
{
"id": "image_builder_client_id",
"type": "promptString",
"description": "Enter the Image Builder Client ID",
"default": ""
},
{
"id": "image_builder_client_secret",
"type": "promptString",
"description": "Enter the Image Builder Client Secret",
"default": ""
}
],
"servers": {
"image-builder-mcp-stdio": {
"type": "stdio",
"command": "podman",
"args": [
"run",
"--env",
"IMAGE_BUILDER_CLIENT_ID",
"--env",
"IMAGE_BUILDER_CLIENT_SECRET",
"--interactive",
"--rm",
"ghcr.io/schuellerf/image-builder-mcp:latest"
],
"env": {
"IMAGE_BUILDER_CLIENT_ID": "${input:image_builder_client_id}",
"IMAGE_BUILDER_CLIENT_SECRET": "${input:image_builder_client_secret}"
}
}
}
}
Cursor
Cursor doesn't seem to support inputs you need to add your credentials in the config file.
To start the integration create a file ~/.cursor/mcp.json with
{
"mcpServers": {
"image-builder-mcp": {
"type": "stdio",
"command": "podman",
"args": [
"run",
"--env",
"IMAGE_BUILDER_CLIENT_ID",
"--env",
"IMAGE_BUILDER_CLIENT_SECRET",
"--interactive",
"--rm",
"ghcr.io/schuellerf/image-builder-mcp:latest"
],
"env": {
"removeprefix_IMAGE_BUILDER_CLIENT_ID": "YOUR_ID here, then remove 'removeprefix_'",
"removeprefix_IMAGE_BUILDER_CLIENT_SECRET": "YOUR_SECRET here, then remove 'removeprefix_'"
}
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.