Skip to main content
Glama
noeltg77

Replicate Designer MCP

by noeltg77
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Replicate Designer MCP

An MCP server for generating images using Replicate's Flux 1.1 Pro model.

Installation

Using Directly from GitHub

You can use the MCP server directly from GitHub in several ways:

Option 1: Install directly with pip

pip install git+https://github.com/yourusername/replicate-designer.git

Then run it with:

mcp-replicate-designer

Option 2: Use npx with GitHub repository

Create a configuration file (e.g., mcps.json):

{
  "mcpServers": {
    "replicateDesigner": {
      "command": "npx",
      "args": [
        "-y", 
        "github:yourusername/replicate-designer"
      ],
      "env": {
        "REPLICATE_API_TOKEN": "your_replicate_api_token_here"
      }
    }
  }
}

Then use it with Claude or another assistant:

npx @anthropic-ai/assistant --mcps-json mcps.json

This method allows you to include your Replicate API token directly in the configuration file, which is more convenient than setting environment variables separately.

Option 3: Local Installation

Clone the repository and install from the local directory:

git clone https://github.com/yourusername/replicate-designer.git
cd replicate-designer
pip install -e .

Publishing and Using via npm

To make your MCP available via npm (for easier distribution):

  1. Package and publish your MCP:

# Build a wheel
pip install build
python -m build

# Publish to npm (after setting up an npm account)
npm init
npm publish

  1. Then users can install and use it directly:

npx -y mcp-replicate-designer

Related MCP server: BFL MCP Server

Usage

Setting the API Token

There are several ways to provide your Replicate API token:

  1. Environment variable (for command line usage):

    export REPLICATE_API_TOKEN=your_api_token_here

  2. In the MCP configuration file (as shown in Option 2 above):

    {
  "mcpServers": {
    "replicateDesigner": {
      "command": "...",
      "args": ["..."],
      "env": {
        "REPLICATE_API_TOKEN": "your_replicate_api_token_here"
      }
    }
  }
}

  3. Using a .env file in your project directory:

    REPLICATE_API_TOKEN=your_api_token_here

    Then, install the python-dotenv package:

    pip install python-dotenv

Security Note: Be careful with your API tokens. Never commit them to public repositories, and use environment variables or secure secret management when possible.

Running the MCP server

mcp-replicate-designer

By default, it runs in stdio mode which is compatible with npx use. You can also run it in SSE mode:

mcp-replicate-designer --transport sse --port 8000

Using with npx

This MCP can be used with an AI agent using npx in two ways:

Direct command line

npx @anthropic-ai/assistant --mcp mcp-replicate-designer

As a configuration object

In your configuration JSON:

{
  "mcpServers": {
    "replicateDesigner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-replicate-designer"
      ]
    }
  }
}

Then use it with:

npx @anthropic-ai/assistant --mcps-json /path/to/your/config.json

Tool

This MCP exposes a single tool:

generate_image

Generates an image using Replicate's Flux 1.1 Pro model.

Parameters:

  • prompt (string, required): Text description of the image to generate

  • aspect_ratio (string, optional, default: "1:1"): Aspect ratio for the generated image

  • output_format (string, optional, default: "webp"): Format of the output image

  • output_quality (integer, optional, default: 80): Quality of the output image (1-100)

  • safety_tolerance (integer, optional, default: 2): Safety tolerance level (0-3)

  • prompt_upsampling (boolean, optional, default: true): Whether to use prompt upsampling

Example:

{
  "prompt": "A photograph of an humanoid AI agent looking sad and in disrepair, the agent is sat at a workbench getting fixed by a human male",
  "aspect_ratio": "1:1",
  "output_format": "webp"
}

Available Tools

1 tool
generate_imageC

Generates an image using Replicate's Flux 1.1 Pro model

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesText description of the image to generate
aspect_ratioNoAspect ratio for the generated image (e.g. '1:1', '16:9', '4:3')1:1
output_formatNoFormat of the output image (e.g. 'webp', 'png', 'jpeg')webp
output_qualityNoQuality of the output image (1-100)
safety_toleranceNoSafety tolerance level (0-3)
prompt_upsamplingNoWhether to use prompt upsampling

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the model used ('Replicate's Flux 1.1 Pro model') but doesn't describe key behavioral traits such as cost implications, rate limits, authentication requirements, processing time, or what happens on failure. For a generative AI tool with potential side effects, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the core functionality without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly. Every word earns its place in conveying the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of an image generation tool with 6 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns (e.g., image URL, binary data, metadata), error conditions, or practical considerations like cost or latency. The description alone leaves significant gaps for an agent to use this tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, meaning all parameters are well-documented in the schema itself. The description adds no additional parameter information beyond what's in the schema. According to the rules, when schema coverage is high (>80%), the baseline score is 3 even with no param info in the description, which applies here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Generates an image') and specifies the resource/technology ('using Replicate's Flux 1.1 Pro model'), making the purpose immediately understandable. However, it lacks differentiation from siblings, but since there are no sibling tools, this doesn't reduce the score. The description is specific but could be more detailed about what type of image generation this provides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It simply states what the tool does without context about appropriate scenarios or limitations. Since there are no sibling tools, the lack of differentiation isn't penalized, but the complete absence of usage context warrants a low score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool update
    • First observedgenerate_image
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool 'generate_image' has a clearly distinct and singular purpose.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'generate_image' follows a clear verb_noun pattern.

Tool Count2/5

A single tool is too few for a server named 'Replicate Designer MCP', which suggests a broader scope related to design or image generation. This minimal set feels thin and incomplete for the implied domain.

Completeness1/5

The tool surface is severely incomplete for a design-oriented server. It only offers image generation, with no tools for editing, transforming, analyzing, or managing images, creating significant gaps that will limit agent functionality.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • BFL MCP Server

    elhombrejd
    F
    license
    B
    quality
    Not graded
    maintenance
    An MCP server that enables generating and editing high-quality images with natural language using Black Forest Labs' FLUX.1 Kontext Pro model.
    2
    5
    -

  • Image MCP Server

    iplanwebsites
    A
    license
    C
    quality
    C
    maintenance
    An MCP server that provides AI image generation capabilities using OpenAI and Replicate APIs with support for customizable prompts and dimensions. It features specialized tools for generating square, landscape, and portrait images through simple natural language commands.
    5
    43
    MIT

  • Nano-Banana MCP Server

    bongartzdiaz
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that provides AI image generation and editing capabilities using Google's Gemini 2.5 Flash Image API. It allows users to create new images from text, modify existing files, and perform iterative edits through natural language prompts.
    6
    758
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/noeltg77/Replicate-Designer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server