Skip to main content
Glama
Sign In
fal-mcp

fal-mcp

by guillaumeboniface
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

fal-mcp

An MCP server that wraps the fal.ai image generation API, giving Claude (or any MCP client) the ability to generate and edit images.

Tools

Tool

Description

generate_image

Text-to-image generation with configurable model, size, steps, and guidance

generate_with_reference

Image generation guided by a style/content reference image

generate_with_lora

Image generation with a LoRA model applied

edit_image

Edit an existing image using natural language instructions (FLUX Kontext)

raw_generate

Submit arbitrary requests for advanced configurations (ControlNet, IP-Adapter, multi-LoRA)

list_outputs

List all saved images in the output directory

Related MCP server: Nano-Banana MCP Server

Supported models

  • fal-ai/flux/dev — high quality (default)

  • fal-ai/flux/schnell — fast, 1-4 steps

  • fal-ai/flux-pro/v1.1 — professional, up to 2K resolution

  • fal-ai/flux-general — supports LoRA, ControlNet, IP-Adapter

  • fal-ai/recraft/v3/text-to-image — illustration style

  • fal-ai/flux-pro/kontext — image editing

Setup

  1. Get an API key from fal.ai

  2. Set the FAL_KEY environment variable (or add it to a .env.local file in the parent directory)

Usage with Claude Code

Add this to your .mcp.json:

{
  "mcpServers": {
    "fal": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/fal-mcp", "python", "server.py"]
    }
  }
}

Dependencies

  • Python >= 3.11

  • FastMCP v2

  • httpx

  • python-dotenv

Available Tools

6 tools
edit_imageB

Edit an existing image using natural language instructions (FLUX Kontext).

Pass a reference image and describe the changes you want in the prompt. Great for iterating on generated images.

Args: image_url: URL of the image to edit. prompt: Description of the desired changes.

Inputs: prompt (required), image_url (required), model, seed, +2 more. Returns: object

generate_imageA

Generate images from a text prompt using fal.ai.

Common models:

  • fal-ai/flux/dev (high quality, 28 steps)

  • fal-ai/flux/schnell (fast, 1-4 steps)

  • fal-ai/flux-pro/v1.1 (professional, up to 2K)

  • fal-ai/flux-general (supports LoRA, ControlNet, IP-Adapter)

  • fal-ai/recraft/v3/text-to-image (illustration style)

Returns paths to saved images and metadata.

Inputs: prompt (required), model, width, height, +6 more. Returns: object

generate_with_loraC

Generate images with a LoRA model applied.

Args: lora_url: URL to the LoRA safetensors file (e.g. from HuggingFace). lora_scale: Strength of the LoRA effect (0.0-2.0, default 1.0).

Inputs: prompt (required), lora_url (required), lora_scale, model, +8 more. Returns: object

generate_with_referenceC

Generate images with a style/content reference image.

Uses the reference_image feature of flux-general to guide generation toward a similar style or content as the reference.

Args: reference_image_url: URL of the reference image for style guidance. reference_strength: How strongly to follow the reference (0.0-1.0).

Inputs: prompt (required), reference_image_url (required), reference_strength, model, +8 more. Returns: object

list_outputsB

List all images previously saved in the output directory.

Inputs: no named parameters. Returns: object

raw_generateA

Submit an arbitrary request to any fal.ai model endpoint.

Use this for advanced configurations (ControlNet, IP-Adapter, multi-LoRA, custom parameters) that aren't covered by the other tools.

Args: model: The fal.ai model endpoint ID (e.g. "fal-ai/flux-general"). body: The full JSON request body to send to the model.

Inputs: model (required), body (required), filename. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 6 tools

    Disambiguation4/5

    Most tools have distinct purposes: edit_image modifies existing images, generate_image creates from text, generate_with_lora adds LoRA models, generate_with_reference uses style guidance, list_outputs enumerates saved images, and raw_generate handles advanced configurations. However, generate_image and generate_with_lora could potentially overlap in functionality if LoRA is used for generation, but their descriptions clarify the distinction.

    Naming Consistency4/5

    Tool names follow a consistent verb-based snake_case pattern (e.g., edit_image, generate_image, list_outputs), which is clear and predictable. The only minor deviation is raw_generate, which uses 'raw' as a prefix instead of a verb, but it still fits the overall naming style without causing confusion.

    Tool Count5/5

    With 6 tools, the server is well-scoped for image generation and editing tasks. Each tool serves a specific role, from basic generation to advanced configurations, and the count is neither too sparse nor overwhelming, fitting typical MCP server ranges for this domain.

    Completeness4/5

    The toolset covers core image generation workflows: creation (generate_image), editing (edit_image), style control (generate_with_reference), model customization (generate_with_lora), and advanced options (raw_generate), plus management (list_outputs). A minor gap is the lack of a delete or manage tool for removing saved images, but agents can work around this.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches