
Replicate
CommunityPopularOfficial Replicate MCP server for running thousands of ML models via API. Generate images with Stable Diffusion, clone voices, upscale video, and chain models into pipelines.
| Publisher | replicate |
| Repository | replicate-mcp |
| Language | TypeScript |
| Forks | 0 |
| Stars | 8.3K |
| Available tools | 16 |
| Transport type | stdio |
| Categories | |
| License | MIT |
| Links |
- Connect tools to AI workflows
Replicate exposes MCP capabilities that can be used by compatible AI clients and agents.
- 16 available tools
Browse the callable actions below, including names and descriptions when provided by the server.
- Ready-to-copy setup
Use the installation snippets to configure this server in your preferred MCP client.
- Open source signals
8.3K stars and 0 forks from the linked repository.
Installation
Node.js 18+
{
"mcpServers": {
"replicate": {
"command": "npx",
"args": [
"-y",
"@replicate/mcp"
],
"env": {
"REPLICATE_API_TOKEN": "<YOUR_API_TOKEN>"
}
}
}
}Available Tools
- list_models
List available ML models on Replicate with optional filtering by category, owner, or capabilities
- get_model_details
Get detailed information about a specific model including schema, examples, and version history
- create_prediction
Create a new prediction by running a model with specified input parameters
- get_prediction_status
Get the current status and results of a prediction by ID
- list_predictions
List your recent predictions with optional filtering by status or date range
- cancel_prediction
Cancel a running prediction to stop processing and avoid further charges
- generate_image
Generate images using text-to-image models like Stable Diffusion with customizable parameters
- upscale_image
Enhance and upscale images using super-resolution models to improve quality and resolution
- process_video
Process videos using video enhancement, style transfer, or other video manipulation models
- clone_voice
Clone or synthesize voices using text-to-speech and voice cloning models
- create_training
Start fine-tuning a model with custom training data and parameters
- get_training_status
Check the progress and results of a model training job
- list_trainings
List your model training jobs with status and completion information
- search_models
Search for models by name, description, or tags across the Replicate model library
- get_account_usage
Get current account usage statistics including compute time and costs
- create_pipeline
Create a pipeline that chains multiple models together for complex workflows
Use Replicate MCP with multiple AI models
TypingMind connects MCP tools at the workspace level, so once Replicate is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.
Setup guide to use the local connector
Use this when the MCP server needs access to local files, apps, or private resources on your computer.
Open the MCP settings
In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.
- Open TypingMind in your browser.
- Click the Settings icon.
- Go to Advanced Settings.
- Open the Model Context Protocol section.
- Click Setup Connector and choose This Device.

Run the connector command
Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.
- Copy the setup command shown by TypingMind.
- Open Terminal on macOS or Windows Terminal on Windows.
- Paste and run the command.
- Approve the package install if Terminal asks you to proceed.
- Keep the Terminal window running while using MCP tools.
Add Replicate as a server
When the connector status is Ready, click Edit Servers and paste the MCP server configuration.
- Wait until the connector status shows Ready.
- Click Edit Servers.
- Paste the Replicate MCP server configuration.
- Save the server list.
- Refresh if you want to confirm the connector is still ready.

{
"mcpServers": {
"replicate": {
"command": "npx",
"args": [
"-y",
"@replicate/mcp"
]
}
}
}Use it across models
Save the server list, open Plugins, enable the Replicate MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.
- Open the Plugins page in TypingMind.
- Enable the Replicate MCP tools.
- Start a chat and choose the AI model you want to use.
- Use the MCP tools in chat or assign them to an AI agent.
- Switch to another AI model whenever needed without reconnecting MCP.


Here is what I found using Replicate.
Frequently asked questions
What is the Replicate MCP server used for?
Replicate is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.
Can I use Replicate MCP with multiple AI models in TypingMind?
Yes. TypingMind connects MCP tools at the workspace level, so you can use Replicate with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.
Why use Replicate MCP with TypingMind?
TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Replicate connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.
How do I connect Replicate MCP to TypingMind?
Replicate runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.
What tools does Replicate MCP provide in TypingMind?
Replicate exposes 16 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.
Do I need to share my API keys with TypingMind to use Replicate MCP?
No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Replicate requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.
Related MCP Servers
View allKnowledge Graph Memory
Model Context Protocol Servers
Context7
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Blender
Experience seamless AI-powered 3D modeling by connecting Blender with Claude AI via the Model Context Protocol. BlenderMCP enables two-way communication, allowing you to create, modify, and inspect 3D scenes directly through AI prompts. Control objects, materials, lighting, and execute Python code in Blender effortlessly. Access assets from Poly Haven and generate AI-driven models using Hyper3D Rodin. This integration enhances creative workflows by combining Blender’s robust tools with Claude’s intelligent guidance, making 3D content creation faster, interactive, and more intuitive. Perfect for artists and developers seeking AI-assisted 3D design within Blender’s environment.
Google GenAI Toolbox
MCP Toolbox for Databases is an open source MCP server for databases.
