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

Use Predibase with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Deploy and query fine-tuned LLMs via Predibase. run inference, classify text, and monitor deployment metrics directly from your 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 · 7 capabilities

The complete Predibase capability set.

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

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Predibase.

  1. 01

    Classify

    Batch classification for one or more inputs

  2. 02

    Get health

    Check health status of the inference endpoint

  3. 03

    Get metrics

    Get Prometheus metrics for the deployment

  4. 04

    Chat completion

    Create a chat completion (OpenAI compatible)

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Predibase.

  1. 05

    Completion

    Create a completion (OpenAI compatible)

  2. 06

    Generate text

    Generate text using a deployed LLM

  3. 07

    Get info

    Get inference endpoint metadata

Observed, not estimated

900ms average. Fast in production.

Predibase is checked daily against the live service.

Daily averagePeak 1244ms
Aug 20Today
Fastest day
721ms
Slowest day
1244ms
14-day trend
Slowing+24%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 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 Predibase, so you can see the experience inside your AI.

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

Predibase Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_anUwoOMv2E6QQVudvBXsDytO30kiB1fpaXuzKUbp/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 — Predibase capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "predibase-llm-serving-finetuning-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_anUwoOMv2E6QQVudvBXsDytO30kiB1fpaXuzKUbp/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 Predibase owners ask.

  • 01

    Can I use my fine-tuned adapters with this server?

    Yes. When using the generate_text capability, you can provide an adapter_id to apply your specific fine-tuned LoRA adapter to the base model deployment.

  • 02

    How do I monitor the performance of my Predibase deployment?

    Use the get_metrics capability to scrape Prometheus-formatted metrics or get_info to retrieve metadata like model ID and device type.

  • 03

    Does this support structured JSON responses?

    Absolutely. The generate_text capability includes a schema parameter that allows you to pass a JSON schema to ensure the model output follows a specific structure.

Explore

More in Developer Tools

Suggestions