Replicate Connector for AI agents.

20 live capabilities

Run and manage machine learning models without setting up a server.

Live agent request Replicate / Connector

Waiting for input…

AI Agent

Why people use Replicate

Replicate for Machine Learning Model Deployment

This Connector removes that entire layer of friction. You just tell your agent what you want to do, and it handles the calls to Replicate. You get to stay in your flow, while the agent handles the model discovery, prediction execution, and status tracking. You get to focus on the results, not the rack.

What Vinkius changes

You get instant access to production-grade machine learning without managing any infrastructure.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

Prompting for Art

A designer wants a specific style of image.
Real-world use case 02

Fine-tuning a Niche Model

A developer needs a model trained on specific company data.
Real-world use case 03

Scaling a Production App

An engineer needs to serve model results to thousands of users.

Complete set · 20capabilities

The complete Replicate capability set.

These are the exact actions your AI can choose when you ask it to work with Replicate.

Capability set01 / 05

01—04

4 capabilities in this set.

Part of 20 available through Replicate.

01 Capability
Cancel prediction
Stop a prediction that is currently running. Use this if you notice a mistake in the input.
02 Capability
Create deployment prediction
Run a prediction using a dedicated deployment. This ensures faster, more reliable results for production.
03 Capability
Create model
Create a new model entry on the Replicate platform. Use this to organize your custom assets.
04 Capability
Create prediction
Trigger a model to run a specific task. It sends your inputs to the model and starts the process.

Capability set02 / 05

05—08

4 capabilities in this set.

Part of 20 available through Replicate.

05 Capability
Create training
Start a new training session to fine-tune a model. This is how you customize models on your own data.
06 Capability
Delete model version
Remove a specific version of a model. Use this to clean up old or broken versions.
07 Capability
Get account
See your account details and organization info. It's the quickest way to check your current status.
08 Capability
Get collection
Pull details for a specific model collection. This helps you see how models are grouped.

Capability set03 / 05

09—12

4 capabilities in this set.

Part of 20 available through Replicate.

09 Capability
Get model version
Get the details and OpenAPI schema for a specific version. This lets your agent understand the exact inputs needed.
10 Capability
Get prediction
Check the status and final output of a prediction. Use this to see if your generation finished.
11 Capability
Get training
Check the current status of a training job. This tells you if your fine-tuning is still running.
12 Capability
Get webhook secret
Retrieve the secret key for your webhooks. You'll need this to verify signatures from Replicate.

Capability set04 / 05

13—16

4 capabilities in this set.

Part of 20 available through Replicate.

13 Capability
List collections
See all curated collections of models. This is a good starting point for finding new capabilities.
14 Capability
List hardware
See all available hardware SKUs. Use this to understand the compute options available to you.
15 Capability
List predictions
See a history of your recent predictions. This is your go-to for looking back at previous runs.
16 Capability
Search models
Search for public models on Replicate. Use this to find the right capability for any ML task.

Capability set05 / 05

17—20

4 capabilities in this set.

Part of 20 available through Replicate.

17 Capability
Update model
Change the metadata for an existing model. This helps you keep your custom model info current.
18 Capability
Create deployment
Set up a private deployment with specific autoscaling rules. This is great for production environments.
19 Capability
Get model
Fetch specific details about a model. This is useful for checking configuration and metadata.
20 Capability
List model versions
See every version of a specific model. This helps you pick the right one for your task.

Set up in minutes

One URL. Then ask Replicate to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Replicate from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Replicate, and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Replicate for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Replicate URL.
Step 03

Save and start

Save the connection and enable Replicate in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "replicate-extended": {
      "url": "https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Replicate

Open Agent mode in chat and ask: "Using Replicate, help me...". 20 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "replicate-extended": {
      "url": "https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Replicate

Ask Copilot: "Using Replicate, help me...". 20 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "replicate-extended": {
      "url": "https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Replicate

Open Cascade and ask: "Using Replicate, help me...". 20 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "replicate-extended": {
      "url": "https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Replicate

Ask Cline: "Using Replicate, help me...". 20 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add replicate-extended --transport http "https://edge.vinkius.com/vk_preview_ULeVbcRjoLCkIr9x93q2HML8VJd4AXmk4CWHHPso/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Replicate

Ask Claude: "Using Replicate, show me...". 20 tools are ready

Where the request belongs

Work Replicate can move forward.

Built around the request

This is for the developer who needs to run heavy ML models but doesn't want to spend a weekend configuring GPU drivers or managing a fleet of inference servers.

01

AI Engineer

Testing different model versions and parameters quickly without writing boilerplate API calls.

02

Creative Technologist

Generating high-quality media assets like images or audio directly within their design workflow.

03

Data Scientist

Monitoring long-running training sessions and checking prediction logs from a single interface.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 12 capabilities

Replicate

Run ML models via Replicate. generate images, text, audio and video from community models, track predictions and explore collections from any AI agent.

02 1 capability

Modelbit (ML Model Deployments)

Deploy and call machine learning models directly from your AI agent using Modelbit's inference endpoints.

03 8 capabilities

Abacus AI (Enterprise AI Cloud)

Manage the full machine learning lifecycle via Abacus AI. create projects, train models, and deploy real-time prediction endpoints.

04 6 capabilities

Baseten

Manage your Baseten AI models. orchestrate deployments, list secrets, and run serverless inference predictions autonomously.

05 15 capabilities

Cerebras Inference

Access lightning-fast AI inference via Cerebras Wafer-Scale Engine. generate chat completions, manage models, and run batch jobs at record speeds.

06 6 capabilities

Arize AI

Monitor ML model performance, detect data drift, and troubleshoot prediction quality with real-time observability dashboards.

Bring your own AI

Change the model, client or framework. Keep Replicate connected.

Before you connect

Questions about Replicate.

The practical details behind the request, access and result.

How does the Replicate MCP help with machine learning?

It lets your AI agent execute models directly. Instead of writing code to call an API, you just tell the agent what to generate or process, and it handles the communication with Replicate's infrastructure.

Can I use this Connector to run Stable Diffusion?

Yes, you can use search_models to find the best version and then run predictions to generate images directly from your chat.

How do I manage my custom models with the Replicate MCP?

You can use it to create, update, and delete models. Your agent can also pull specific versions and their schemas to ensure it's sending the right data.

Can my agent monitor my model training?

Absolutely. Use the get_training capability to check progress. Your agent can even give you updates as the training moves through different stages.

Is it possible to scale my model for production?

Yes, you can use create_deployment to set up a private deployment with autoscaling, which is perfect for handling high traffic.

How do I know what inputs a specific Replicate model needs?

The Connector can fetch the OpenAPI schema for any model version. This allows your agent to see exactly what parameters are required before it tries to run a prediction.

How can I check if my prediction has finished and see the output?

Use the get_prediction capability with your Prediction ID. It will return the current status (starting, processing, succeeded, or failed) along with the output URLs or data once completed.

Can I search for specific types of models like 'image-to-text'?

Yes! Use the search_models capability with your query. It will return a list of public models matching your terms, including their owners and descriptions.

Is it possible to stop a model that is taking too long to run?

Absolutely. Use the cancel_prediction capability with the target Prediction ID to immediately stop the execution and prevent further usage costs.

One connection away

Give your agent a direct line to Replicate.

Connect Replicate once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available