An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Predibase LLM Serving Finetuning to your AI

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. Deploy and query fine-tuned models directly from your agent.

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 · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Predibase.

  1. 01

    Get metrics

    This capability pulls Prometheus metrics to monitor your deployment performance.

  2. 02

    Classify

    This capability performs batch classification on one or more inputs to categorize text data.

  3. 03

    Get health

    Use this to check the current health status of your inference endpoint.

  4. 04

    Chat completion

    This capability creates chat completions using an OpenAI compatible interface.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Predibase.

  1. 05

    Completion

    This capability generates text completions through an OpenAI compatible interface.

  2. 06

    Generate text

    This capability triggers text generation from any of your deployed LLMs.

  3. 07

    Get info

    Use this to retrieve metadata regarding your specific inference endpoints.

Real work

What teams actually run

01

Model Testing

Test how a fine-tuned model responds to specific prompts directly in your IDE.

02

Production Monitoring

Check if an inference endpoint is healthy or lagging using real-time metrics.

03

Data Labeling

Run batch classification on large datasets to categorize text automatically.

04

App Development

Use structured JSON outputs to feed model responses into other software capabilities.

Automate a task

Put Predibase 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

Predibase 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 Predibase 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

951ms average. Fast in production.

Predibase is checked daily against the live service.

Daily averagePeak 1176ms
Oct 3Today
Fastest day
710ms
Slowest day
1176ms
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. 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

Guided setup for Claude? Set up Predibase in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Predibase owners hand off.

This MCP is built for technical users who need to bridge the gap between model training and real-time inference.

  • 01

    AI Engineers

    They use the MCP to deploy and test fine-tuned models without leaving their chat interface.

  • 02

    Data Scientists

    They monitor the health and performance metrics of production deployments.

  • 03

    Developers

    They integrate high-performance LLM capabilities into apps using structured JSON.

FAQ

Questions Predibase owners ask.

  • 01

    How do I use my fine-tuned models?

    You can use the generate_text capability and specify the adapter_id parameter to apply your LoRA adapters during inference.

  • 02

    Which AI clients can I use with this MCP?

    You can connect this MCP to any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I monitor my model's performance?

    Yes, you can use get_health to check endpoint status and get_metrics to pull Prometheus data for monitoring.

  • 04

    Is the inference OpenAI compatible?

    Yes, the chat_completion and completion capabilities follow OpenAI compatible formats.

  • 05

    What do I need to get started?

    You will need your Predibase API Token and your Tenant ID to authenticate the connection.

  • 06

    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.

  • 07

    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.

  • 08

    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

Connect Predibase to Claude, Cursor, ChatGPT & more