An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Replicate to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run massive open-source models through simple text commands.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Replicate API.

  1. 01

    Cancel prediction

    This capability stops a running prediction immediately. Use it when a model task is no longer needed or is behaving unexpectedly.

  2. 02

    Get account

    This capability fetches your Replicate account details. It helps your agent verify your identity and account status.

  3. 03

    Get collection

    This capability retrieves a specific group of models using its slug. It's useful for browsing curated sets like text-to-image models.

  4. 04

    Get model

    This capability pulls detailed information about a specific model. Your agent uses this to learn the exact input schema needed for a prediction.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Replicate API.

  1. 05

    Get prediction

    This capability checks the status and retrieves the final output of a prediction. Use it to see if a model has finished its task.

  2. 06

    List collections

    This capability shows you the various curated model collections available. It helps your agent discover organized groups of models.

  3. 07

    List deployments

    This capability lists your active model deployments. It provides a view of what you currently have running on the platform.

  4. 08

    List models

    This capability returns a list of public models. It's the starting point for broad discovery across the platform.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Replicate API.

  1. 09

    List predictions

    This capability shows your recent prediction history. Use it to review past tasks and their results.

  2. 10

    Search models

    This capability searches the Replicate library for models matching your keywords. It's how your agent finds specific capabilities like TTS or video generation.

  3. 11

    Create prediction

    This capability starts a new model prediction. You provide the model version and the input variables to begin a task.

  4. 12

    List hardware

    This capability lists the GPU hardware options available. It helps you understand the underlying compute power for running models.

Real work

What teams actually run

01

Rapid Prototyping

Quickly test how a specific model responds to different prompts without setting up a dev environment.

02

Automated Media Generation

Trigger video or image generation tasks as part of a larger conversational workflow.

03

Model Comparison

Search for and run multiple models with the same prompt to compare their outputs.

04

Workflow Orchestration

Use an agent to chain together different models for complex multi-step tasks.

Automate a task

Put Replicate API to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Replicate API works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Replicate API to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

899ms average. Fast in production.

Replicate API is checked daily against the live service.

Daily averagePeak 1227ms
Oct 3Today
Fastest day
676ms
Slowest day
1227ms
14-day trend
Stable-4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Replicate API, so you can see the experience inside your AI.

It does not authenticate your account with Replicate API. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Replicate API Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_ZjGhumvOdiFG6C4qZnstV0k6xajsQmuKnK85lhvV/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Replicate API capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "replicate-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ZjGhumvOdiFG6C4qZnstV0k6xajsQmuKnK85lhvV/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Replicate API in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Replicate API owners hand off.

This MCP is built for anyone who needs to use high-end machine learning models without managing local infrastructure.

  • 01

    AI Developers

    Test new open-source algorithms by sending predictions via text instead of writing Python code.

  • 02

    Content Creators

    Delegate image, audio, or video generation tasks to an agent that can trigger Replicate models.

  • 03

    Builders

    Combine outputs from different specialized models using natural language instructions.

FAQ

Questions Replicate API owners ask.

  • 01

    Do I need a GPU to use this MCP?

    No. All model execution happens on Replicate's hardware, not your local machine.

  • 02

    How do I provide my credentials?

    You need to add your Replicate API Token to the MCP configuration settings after connecting.

  • 03

    Can I stop a model that is currently running?

    Yes. You can use the cancel_prediction capability to stop any active task immediately.

  • 04

    What kind of models can I run?

    You can run any open-source machine learning model available on the Replicate platform, including image, video, and audio models.

  • 05

    How does the agent know what inputs a model needs?

    The agent uses the get_model capability to retrieve the exact schema and parameter requirements for any model you select.

  • 06

    Can the agent pass a JSON payload directly into a Replicate model?

    Yes. You can utilize the create_prediction action and attach the payload parameter filled out with any required input schema (e.g., specific prompt, num_inference_steps). Since models change inputs constantly, you should always ask your assistant to fetch the schema details first via get_model to verify keys.

  • 07

    Does the prediction command return results instantly?

    No, Replicate's API operates asynchronously. The initial command gives your assistant an ID. You must then ask your AI companion to query the get_prediction capability periodically using that generated ID until it displays the completed status along with the generated web URLs or generated strings.

  • 08

    Can the AI browse trending or curated model collections?

    Yes. Use the list_collections capability to browse curated groups of models organized by category. such as image generation, text-to-speech, or video. Each collection includes a slug and description so you can quickly identify the right set of models for your use case.

Explore

More in Superpower

Suggestions

Connect Replicate API to Claude, Cursor, ChatGPT & more