> For the complete documentation index, see [llms.txt](https://docs.flora.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flora.ai/mcp/recipes.md).

# FLORA MCP recipes

Step-by-step FLORA MCP recipes for common jobs: generate, animate, batch, run Techniques, upload files, arrange the canvas, iterate and brief your agent.

Each recipe is one job you can hand to your agent once [FLORA MCP](https://flora.ai/mcp) is connected. It gives you a prompt to copy, then the exact `flora_*` tool calls the agent makes, so you know what to expect and an agent can follow it step by step. Not connected yet? Start with the [quickstart](https://docs.flora.ai/mcp/quickstart.md).

## Find a recipe by job

| I want to…                                    | Recipe                                                                                       | Key tools                                                                       |
| --------------------------------------------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| Make a few images, a video, 3D, audio or text | [Generate an image or video](https://docs.flora.ai/mcp/recipes/generate.md)                  | `flora_list_models`, `flora_create_generations`, `flora_list_generations`       |
| Animate a product photo                       | [Turn a product photo into video](https://docs.flora.ai/mcp/recipes/image-to-video.md)       | `flora_create_generations`, or `flora_add_to_canvas` + `flora_run_canvas_nodes` |
| Make one asset per row of a list (20 to 500)  | [Batch-generate 20 to 500 assets](https://docs.flora.ai/mcp/recipes/batch.md)                | `flora_create_generations` (20 per call), `flora_list_generations`              |
| Run a saved workflow my team built            | [Run your team's Technique](https://docs.flora.ai/mcp/recipes/run-a-technique.md)            | `flora_list_techniques`, `flora_get_technique`, `flora_run_technique`           |
| Use my own images, video, audio or PDFs       | [Upload your own images, video and files](https://docs.flora.ai/mcp/recipes/upload-files.md) | `flora_create_asset` (with `project_id`), `flora_complete_asset`                |
| Lay results out as a grid or a board          | [Put results on a canvas](https://docs.flora.ai/mcp/recipes/canvas.md)                       | `flora_arrange_canvas`, `flora_add_to_canvas`, `flora_organize_canvas_fields`   |
| Get more like the ones I liked                | [Iterate on favorites](https://docs.flora.ai/mcp/recipes/iterate.md)                         | `flora_create_generations` with `reference_node_ids`                            |
| Get better results from my agent              | [Brief your agent for better output](https://docs.flora.ai/mcp/recipes/prompting.md)         | (any)                                                                           |

## Choosing between neighbours

* **Generate, batch or Technique?** Use [generate](https://docs.flora.ai/mcp/recipes/generate.md) for up to 20 one-off items in a single call. Use [batch](https://docs.flora.ai/mcp/recipes/batch.md) when the input is a list and every row gets the same style; it adds quoting the whole batch, chunking, and retrying only failures. Use a [Technique](https://docs.flora.ai/mcp/recipes/run-a-technique.md) when your team has already saved the steps, prompts and models; for a list, run one Technique per row with the batch method.
* **Generate or image to video?** A video from a prompt alone is [generate](https://docs.flora.ai/mcp/recipes/generate.md). A video that starts from a photo is [image to video](https://docs.flora.ai/mcp/recipes/image-to-video.md).
* **Iterate or generate again?** If the new images should look like earlier ones, [iterate](https://docs.flora.ai/mcp/recipes/iterate.md) passes the earlier outputs as references. Generating again from the same prompt only re-rolls.

## Rules every recipe follows

{% hint style="warning" %}
**Cost rule.** Price first: call `flora_create_generations` with `quote: true` and show the user the cost in US dollars. Run the same request without `quote` only after they approve. On `insufficient_credits` or any `BILLING_*` error, stop and pass the message on. Don't retry. Check balance and spend with `flora_get_usage`. A failed run isn't charged; a retry is a new run and is billed again.
{% endhint %}

{% hint style="info" %}
**Polling rule.** Save every `run_id`. Wait at least 15 seconds between polls, or 2 seconds per run for bigger batches (40 seconds for 20 runs). Then read every `run_id` in one `flora_list_generations` call (up to 20 per call). For example: `flora_list_generations({"run_ids": ["run_a", "run_b"]})`. For Technique runs, also pass `"technique_id"`. Polling faster returns `429` or cooldown errors with `retry_after_seconds`.
{% endhint %}

The details behind these rules are in [FLORA MCP cost, balance and limits](https://docs.flora.ai/mcp/cost-and-limits.md) and [FLORA MCP runs: polling, timeouts and failures](https://docs.flora.ai/mcp/runs.md). Every tool and argument is in the [tools reference](https://docs.flora.ai/mcp/tools.md), and the [skills](https://docs.flora.ai/mcp/skills.md) package many of these recipes as instructions your agent can load.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.flora.ai/mcp/recipes.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
