Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Replicate with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Run ML models via Replicate. generate images, text, audio and video from community models, track predictions and explore collections from any AI agent.

Included with plan

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

Complete set · 12 capabilities

The complete Replicate capability set.

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

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Replicate.

  1. 01

    Create prediction

    Requires the model slug in "owner/name" format and an input object matching the model's schema. Optionally specify a version ID and webhook URL. Returns the prediction object with its ID, status (starting, processing, succeeded, failed, canceled) and output. Use get_prediction to check status and retrieve results. Run a model prediction on Replicate

  2. 02

    Get account

    Returns account type, username and usage info. Use this to verify your API token is working correctly. Get the authenticated Replicate account info

  3. 03

    Get collection

    Provide the collection slug (e.g. "text-to-image", "large-language-models"). Get details for a specific model collection

  4. 04

    Get model

    Provide the model slug in "owner/name" format (e.g. "stability-ai/sdxl" or "meta/meta-llama-3-70b-instruct"). Get details for a specific Replicate model

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Replicate.

  1. 05

    Get model versions

    Each version includes its ID (64-char hash), creation date, input/output schema and cog version. Use this to find the correct version ID when creating predictions for models that require a specific version. Get all versions of a Replicate model

  2. 06

    Search models

    Returns models with their name, owner, description, run count and hardware. Useful for finding specific types of models (e.g. "text-to-image", "llm", "music-generation"). Search for models on Replicate by query

  3. 07

    Get prediction

    Returns the prediction ID, status (starting, processing, succeeded, failed, canceled), input, output URLs, creation time and logs. Use the prediction ID returned from create_prediction. Get the status and result of a prediction

  4. 08

    List collections

    Collections group related models by category (e.g. "text-to-image", "large-language-models", "audio-to-audio", "image-to-video"). Each collection includes its slug, name, description and featured models. List model collections on Replicate

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Replicate.

  1. 09

    List hardware

    Each hardware option includes its SKU name, pricing and specifications. Useful for choosing the right GPU for your prediction workload. List available GPU hardware on Replicate

  2. 10

    List models

    Each model includes its name, owner, description, run count, hardware requirements and cover image URL. Use this to discover available models for running predictions. List available ML models on Replicate

  3. 11

    List predictions

    Each prediction includes its ID, model, status, creation time and output URLs. Useful for tracking prediction history and monitoring model usage. List recent predictions on Replicate

  4. 12

    Cancel prediction

    Provide the prediction ID. The prediction status will change to "canceled". Cancel a running prediction

Observed, not estimated

908ms average. Fast in production.

Replicate is checked daily against the live service.

Daily averagePeak 1113ms
Aug 20Today
Fastest day
731ms
Slowest day
1113ms
14-day trend
Slowing+18%

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, so you can see the experience inside your AI.

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

Replicate Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_M4yBN2KNxSS8lU5z0YgsZ7knjRqsTTpfrLzeO7vW/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 capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "replicate-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_M4yBN2KNxSS8lU5z0YgsZ7knjRqsTTpfrLzeO7vW/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

FAQ

Questions Replicate owners ask.

  • 01

    How do I get a Replicate API token?

    Log in to the Replicate API Tokens page and click Create API Token. Copy the token immediately. it starts with r8_ and won't be shown again.

  • 02

    How do I run a model prediction?

    Use create_prediction with the model slug (e.g. "stability-ai/sdxl") and an input JSON object matching the model's schema. The prediction starts as 'starting', then 'processing', and finally 'succeeded' with output URLs. Use get_prediction to check status and retrieve results.

  • 03

    How do I find models for specific tasks?

    Use search_models with a query like 'text-to-image', 'llm', 'music-generation' or 'video-generation'. You can also use list_collections to browse curated collections by category, and get_collection to see featured models in each collection.

  • 04

    Can I cancel a running prediction?

    Yes! Use cancel_prediction with the prediction ID. This works for predictions that are 'starting' or 'processing'. The status will change to 'canceled' and you won't be charged for the full compute time.

Explore

More in AI Frontier

Suggestions