Skip to main content
Connect BeeAI Framework to Magic Hour MCP for image generation and recovery. This command-line example uses the framework’s native tool calls without a language model or another provider key.
Verified October 24, 2026 with BeeAI Framework 0.1.85 / MCP 1.30.0: 48 discovered tools, an authenticated account check, one accepted image creation, same-ID status retrieval, and download from the exact returned HTTPS image URL produced a usable 640×640 PNG. Full image decode passed. This verification used native tool calls without a language model.

​
Install and configure

Requires Python 3.11–3.13. Copy magic_hour.py and requirements.txt into an empty directory, then run:
Provide your Magic Hour API key through your secret manager as MAGIC_HOUR_API_KEY. The MCP endpoint is fixed to https://mcp.magichour.ai/; the example disables logging and OpenTelemetry and does not print account fields, credentials, prompts, or signed download URLs.
The authorization command prints only its status, discovered tool count, and action count. Public tool discovery alone does not prove the API key works.

​
Create one image

The create command sends your prompt to Magic Hour and spends credits. It requests one square 640px Flux 2 Klein image, starting at 5 credits. Run it once for each intended image:
The example calls the native generation tool once and writes the accepted project ID to image-project.txt before returning. It does not poll or automatically repeat creation. The exclusive ID file prevents accidentally submitting the same command twice. If the response is interrupted, the file retains an unknown-outcome marker. Check your Magic Hour projects before submitting another creation. A timeout does not prove the job failed. If saving the accepted ID fails, the ID is still printed so you can preserve it.

​
Retrieve and download

Use the saved ID for all subsequent reads:
get prints the ID and current status. download reads the saved job once and saves its first returned image when the status is complete. It does not poll; run it again later if the job is still queued or rendering. These commands reuse the same project. An unfinished job or failed download never triggers a new generation. Keep the saved ID and retry recovery after the job completes. An existing output file is not overwritten.

​
Use in your application

The example connects over Streamable HTTP, adapts tools with MCPTool.from_session, and executes BeeAI MCPTool.run. Per-tool retries are explicitly zero. The session and transport close on exit. It does not construct a model-backed agent. BeeAI prefers a tool’s structured JSON result and does not retain parallel inline image content in that result, so download uses the exact HTTPS URL returned by the native tool. The media request has no Magic Hour API headers and does not follow redirects. For a model-backed agent, expose only the tools your workflow needs and require explicit approval before paid creation. The native tool recipe does not establish model-driven behavior. See the framework source and our privacy policy. Tool errors are reported without printing private provider responses.