---
title: Tools reference | FLORA API
description: Every tool the FLORA MCP server exposes, grouped by resource.
---

FLORA MCP mirrors the [FLORA REST API](/api/index.md) 1:1 — every API operation is exposed as a callable tool. The agent driving your client decides which tool to call based on your prompt and the tool descriptions, then renders results inline.

This page covers what tools are available and when each is used. For exact request and response schemas, follow the **API Reference** link in each section — both surfaces share the same data shapes.

## Techniques

Discovering Techniques and starting Technique runs is the core FLORA MCP workflow.

| Tool                     | When the agent uses it                                    |
| ------------------------ | --------------------------------------------------------- |
| `list_techniques`        | ”What Techniques do I have?”, “Find Techniques that do X” |
| `retrieve_technique`     | Before running, to inspect inputs and cost                |
| `create_technique_run`   | When the user says “run”, “generate”, “make this”         |
| `retrieve_technique_run` | To poll a previously created run                          |

→ **[API Reference: Techniques](/api/techniques/index.md)**

## Runs

Two top-level run endpoints exist in addition to the slug-based Technique runs above. The agent picks them when the user gives a Technique ID rather than a slug, or asks for a generic generation.

| Tool                   | When the agent uses it                                                    |
| ---------------------- | ------------------------------------------------------------------------- |
| `start_technique_run`  | User refers to a Technique by ID, or chains from earlier results          |
| `start_generation_run` | User asks for a plain image/video generation without a specific Technique |

→ **[API Reference: Runs](/api/runs/index.md)**

## Assets

For workflows that need user-supplied images or videos, the agent creates an asset, uploads bytes via a signed URL, marks it complete, and passes the final URL as a Technique input.

| Tool             | When the agent uses it                                                       |
| ---------------- | ---------------------------------------------------------------------------- |
| `create_asset`   | User says “use this image” with a file path; client uploads on user’s behalf |
| `complete_asset` | After upload finishes                                                        |
| `retry_asset`    | If the signed upload URL expired                                             |
| `list_assets`    | ”Show me my recent uploads”                                                  |
| `retrieve_asset` | Look up a specific asset by ID                                               |

→ **[API Reference: Assets](/api/assets/index.md)**

## Projects

Projects organize Technique runs and uploaded assets inside a workspace. When the agent creates runs, it can optionally tie them to a project so they appear together in the FLORA canvas.

| Tool                   | When the agent uses it                   |
| ---------------------- | ---------------------------------------- |
| `list_projects`        | ”What projects do I have?”               |
| `create_project`       | ”Make a new project for this campaign”   |
| `retrieve_project`     | Inspect a specific project               |
| `list_project_nodes`   | ”What’s in this project?”                |
| `attach_project_asset` | ”Add this output to my campaign project” |

→ **[API Reference: Projects](/api/projects/index.md)**

## Workspaces

| Tool              | When the agent uses it                                                     |
| ----------------- | -------------------------------------------------------------------------- |
| `list_workspaces` | First call after OAuth, or when the user has access to multiple workspaces |

→ **[API Reference: Workspaces](/api/workspaces/index.md)**

## Models

For generic generation workflows that take a model parameter, the agent lists models to discover available IDs.

| Tool          | When the agent uses it         |
| ------------- | ------------------------------ |
| `list_models` | ”What image models can I use?” |

→ **[API Reference: Models](/api/models/index.md)**

## Feedback

| Tool              | When the agent uses it                                                     |
| ----------------- | -------------------------------------------------------------------------- |
| `record_feedback` | User says “this one is great” or “this one is bad” about a specific output |

→ **[API Reference: Feedback](/api/feedback/index.md)**

## How the agent picks tools

You don’t call tools directly. You describe what you want, and the agent picks a sequence. For example, *“Run the Thumbnail Technique with this brief”* typically resolves to:

1. `list_techniques` (with filter `name~"thumbnail"`) — find the right Technique.
2. `retrieve_technique` — see what inputs it needs.
3. `create_technique_run` — submit the run with the inputs you provided.
4. `retrieve_technique_run` (polled) — wait until it’s complete and render outputs inline.

Different prompts produce different sequences. The [Recipes](/mcp/recipes/discover-and-run/index.md) section walks through several end-to-end.

## Tool naming in your client

Most clients namespace tools by server. In Claude Code’s `/mcp` listing they’ll appear as `flora:list_techniques`, in Cursor as `flora.list_techniques`, etc. You almost never need to type these — say what you want and the agent picks the tool.

## Limits and credits

- Calls that create runs (`create_technique_run`, `start_generation_run`) charge your workspace credits. The cost is shown in `retrieve_technique` under `runCost` and on the completed run as `chargedCost`.
- Rate limits apply at the workspace level and match the REST API. See the [API Reference](/api/index.md) for current limits.
- A `402 insufficient_credits` from a tool means the workspace is out of credits — top up in FLORA → Settings → Billing.