# MCP Server Replicate
[](https://www.python.org/downloads/)
[](LICENSE)
[](https://github.com/psf/black)
[](https://github.com/python/mypy)
[](https://github.com/astral-sh/ruff)
[](https://pypi.org/project/mcp-server-replicate/)
A FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference with a focus on image generation.
## Features
- 🖼️ Resource-based image generation and management
- 🔄 Real-time updates through subscriptions
- 📝 Template-driven parameter configuration
- 🔍 Comprehensive model discovery and selection
- 🪝 Webhook integration for external notifications
- 🎨 Quality and style presets for optimal results
- 📊 Progress tracking and status monitoring
- 🔒 Secure API key management
## Available Prompts
The server provides several specialized prompts for different tasks:
### Text to Image (Primary)
Our most thoroughly tested and robust prompt. Optimized for generating high-quality images from text descriptions with:
- Detailed style control
- Quality presets (draft, balanced, quality, extreme)
- Size and aspect ratio customization
- Progress tracking and real-time updates
Example:
```
Create a photorealistic mountain landscape at sunset with snow-capped peaks, quality level: quality, style: photorealistic
```
### Other Prompts
- **Image to Image**: Transform existing images (coming soon)
- **Model Selection**: Get help choosing the right model for your task
- **Parameter Help**: Understand and configure model parameters
## Prerequisites
- Python 3.11 or higher
- A Replicate API key (get one at https://replicate.com/account)
- [UV](https://github.com/astral-sh/uv) for dependency management
## Installation
You can install the package directly from PyPI:
```bash
# Using UV (recommended)
uv pip install mcp-server-replicate
# Using UVX for isolated environments
uvx install mcp-server-replicate
# Using pip
pip install mcp-server-replicate
```
## Claude Desktop Integration
1. Make sure you have the latest version of Claude Desktop installed
2. Open your Claude Desktop configuration:
```bash
# macOS
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
# Windows
code %APPDATA%\Claude\claude_desktop_config.json
```
3. Add the server configuration using one of these options:
```json
{
"globalShortcut": "Shift+Alt+A",
"mcpServers": {
"replicate": {
"command": "uv",
"args": ["tool", "run", "mcp-server-replicate"],
"env": {
"REPLICATE_API_TOKEN": "APITOKEN"
},
"cwd": "$PATH_TO_REPO"
}
}
}
```
4. Set your Replicate API key:
```bash
# Option 1: Set in your environment
export REPLICATE_API_TOKEN=your_api_key_here
# Option 2: Create a .env file in your home directory
echo "REPLICATE_API_TOKEN=your_api_key_here" > ~/.env
```
5. Restart Claude Desktop completely
You should now see the 🔨 icon in Claude Desktop, indicating that the MCP server is available.
## Usage
Once connected to Claude Desktop, you can:
1. Generate images with natural language:
```
Create a photorealistic mountain landscape at sunset with snow-capped peaks
```
2. Browse your generations:
```
Show me my recent image generations
```
3. Search through generations:
```
Find my landscape generations
```
4. Check generation status:
```
What's the status of my last generation?
```
## Troubleshooting
### Server not showing up in Claude Desktop
1. Check the Claude Desktop logs:
```bash
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
```
2. Verify your configuration:
- Make sure the path in `claude_desktop_config.json` is absolute
- Ensure UV is installed and in your PATH
- Check that your Replicate API key is set
3. Try restarting Claude Desktop
For more detailed troubleshooting, see our [Debugging Guide](docs/debugging.md).
## Documentation
- [Implementation Plan](PLAN.md)
- [Contributing Guide](CONTRIBUTING.md)
- [API Reference](docs/api.md)
- [Resource System](docs/resources.md)
- [Template System](docs/templates.md)
## Development
1. Clone the repository:
```bash
git clone https://github.com/gerred/mcp-server-replicate.git
cd mcp-server-replicate
```
2. Install development dependencies:
```bash
uv pip install --system ".[dev]"
```
3. Install pre-commit hooks:
```bash
pre-commit install
```
4. Run tests:
```bash
pytest
```
## Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "mcp-server-replicate",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "ai, image-generation, inference, mcp, replicate, stable-diffusion",
"author": null,
"author_email": "Gerred Dillon <hello@gerred.org>",
"download_url": "https://files.pythonhosted.org/packages/da/8d/bc6e6c3130e2fe2ad17ee5d6cf7555bfc887e840cdd85bf99d9cfbdee567/mcp_server_replicate-0.1.9.tar.gz",
"platform": null,
"description": "# MCP Server Replicate\n\n[](https://www.python.org/downloads/)\n[](LICENSE)\n[](https://github.com/psf/black)\n[](https://github.com/python/mypy)\n[](https://github.com/astral-sh/ruff)\n[](https://pypi.org/project/mcp-server-replicate/)\n\nA FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference with a focus on image generation.\n\n## Features\n\n- \ud83d\uddbc\ufe0f Resource-based image generation and management\n- \ud83d\udd04 Real-time updates through subscriptions\n- \ud83d\udcdd Template-driven parameter configuration\n- \ud83d\udd0d Comprehensive model discovery and selection\n- \ud83e\ude9d Webhook integration for external notifications\n- \ud83c\udfa8 Quality and style presets for optimal results\n- \ud83d\udcca Progress tracking and status monitoring\n- \ud83d\udd12 Secure API key management\n\n## Available Prompts\n\nThe server provides several specialized prompts for different tasks:\n\n### Text to Image (Primary)\n\nOur most thoroughly tested and robust prompt. Optimized for generating high-quality images from text descriptions with:\n\n- Detailed style control\n- Quality presets (draft, balanced, quality, extreme)\n- Size and aspect ratio customization\n- Progress tracking and real-time updates\n\nExample:\n\n```\nCreate a photorealistic mountain landscape at sunset with snow-capped peaks, quality level: quality, style: photorealistic\n```\n\n### Other Prompts\n\n- **Image to Image**: Transform existing images (coming soon)\n- **Model Selection**: Get help choosing the right model for your task\n- **Parameter Help**: Understand and configure model parameters\n\n## Prerequisites\n\n- Python 3.11 or higher\n- A Replicate API key (get one at https://replicate.com/account)\n- [UV](https://github.com/astral-sh/uv) for dependency management\n\n## Installation\n\nYou can install the package directly from PyPI:\n\n```bash\n# Using UV (recommended)\nuv pip install mcp-server-replicate\n\n# Using UVX for isolated environments\nuvx install mcp-server-replicate\n\n# Using pip\npip install mcp-server-replicate\n```\n\n## Claude Desktop Integration\n\n1. Make sure you have the latest version of Claude Desktop installed\n2. Open your Claude Desktop configuration:\n\n```bash\n# macOS\ncode ~/Library/Application\\ Support/Claude/claude_desktop_config.json\n\n# Windows\ncode %APPDATA%\\Claude\\claude_desktop_config.json\n```\n\n3. Add the server configuration using one of these options:\n\n```json\n{\n \"globalShortcut\": \"Shift+Alt+A\",\n \"mcpServers\": {\n \"replicate\": {\n \"command\": \"uv\",\n \"args\": [\"tool\", \"run\", \"mcp-server-replicate\"],\n \"env\": {\n \"REPLICATE_API_TOKEN\": \"APITOKEN\"\n },\n \"cwd\": \"$PATH_TO_REPO\"\n }\n }\n}\n```\n\n4. Set your Replicate API key:\n\n```bash\n# Option 1: Set in your environment\nexport REPLICATE_API_TOKEN=your_api_key_here\n\n# Option 2: Create a .env file in your home directory\necho \"REPLICATE_API_TOKEN=your_api_key_here\" > ~/.env\n```\n\n5. Restart Claude Desktop completely\n\nYou should now see the \ud83d\udd28 icon in Claude Desktop, indicating that the MCP server is available.\n\n## Usage\n\nOnce connected to Claude Desktop, you can:\n\n1. Generate images with natural language:\n\n ```\n Create a photorealistic mountain landscape at sunset with snow-capped peaks\n ```\n\n2. Browse your generations:\n\n ```\n Show me my recent image generations\n ```\n\n3. Search through generations:\n\n ```\n Find my landscape generations\n ```\n\n4. Check generation status:\n ```\n What's the status of my last generation?\n ```\n\n## Troubleshooting\n\n### Server not showing up in Claude Desktop\n\n1. Check the Claude Desktop logs:\n\n```bash\ntail -n 20 -f ~/Library/Logs/Claude/mcp*.log\n```\n\n2. Verify your configuration:\n\n- Make sure the path in `claude_desktop_config.json` is absolute\n- Ensure UV is installed and in your PATH\n- Check that your Replicate API key is set\n\n3. Try restarting Claude Desktop\n\nFor more detailed troubleshooting, see our [Debugging Guide](docs/debugging.md).\n\n## Documentation\n\n- [Implementation Plan](PLAN.md)\n- [Contributing Guide](CONTRIBUTING.md)\n- [API Reference](docs/api.md)\n- [Resource System](docs/resources.md)\n- [Template System](docs/templates.md)\n\n## Development\n\n1. Clone the repository:\n\n```bash\ngit clone https://github.com/gerred/mcp-server-replicate.git\ncd mcp-server-replicate\n```\n\n2. Install development dependencies:\n\n```bash\nuv pip install --system \".[dev]\"\n```\n\n3. Install pre-commit hooks:\n\n```bash\npre-commit install\n```\n\n4. Run tests:\n\n```bash\npytest\n```\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
"bugtrack_url": null,
"license": null,
"summary": "FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference",
"version": "0.1.9",
"project_urls": {
"Documentation": "https://github.com/gerred/mcp-server-replicate#readme",
"Homepage": "https://github.com/gerred/mcp-server-replicate",
"Issues": "https://github.com/gerred/mcp-server-replicate/issues"
},
"split_keywords": [
"ai",
" image-generation",
" inference",
" mcp",
" replicate",
" stable-diffusion"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5153a1214e35e065cc9f9d7c7390cc48fe8ef031a7cc72eddc64a4a3a5121041",
"md5": "d9528da429249653dce96ed6cde7f3b6",
"sha256": "46ccace97d1c5336074cfc2e69584aa8508686435f7c2a38ef99c4a005cbe13d"
},
"downloads": -1,
"filename": "mcp_server_replicate-0.1.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d9528da429249653dce96ed6cde7f3b6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 3770,
"upload_time": "2025-01-06T23:10:21",
"upload_time_iso_8601": "2025-01-06T23:10:21.008408Z",
"url": "https://files.pythonhosted.org/packages/51/53/a1214e35e065cc9f9d7c7390cc48fe8ef031a7cc72eddc64a4a3a5121041/mcp_server_replicate-0.1.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "da8dbc6e6c3130e2fe2ad17ee5d6cf7555bfc887e840cdd85bf99d9cfbdee567",
"md5": "084f6f395d48f7f4561c682f4e53fe72",
"sha256": "e89858a7b39e3ec542502cffda84d1aa4c5f638902353f927c5b0575ed65ac1d"
},
"downloads": -1,
"filename": "mcp_server_replicate-0.1.9.tar.gz",
"has_sig": false,
"md5_digest": "084f6f395d48f7f4561c682f4e53fe72",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 30187,
"upload_time": "2025-01-06T23:10:23",
"upload_time_iso_8601": "2025-01-06T23:10:23.098499Z",
"url": "https://files.pythonhosted.org/packages/da/8d/bc6e6c3130e2fe2ad17ee5d6cf7555bfc887e840cdd85bf99d9cfbdee567/mcp_server_replicate-0.1.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-06 23:10:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "gerred",
"github_project": "mcp-server-replicate#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "mcp-server-replicate"
}