An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Gradient AI LLM API Finetuning to ChatGPT and Claude

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. Train custom models and run NLP tasks through 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 · 19 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 19 available through Gradient AI.

  1. 01

    Personalize document

    This capability rewrites a document to suit a specific audience.

  2. 02

    Upload file

    Use this to upload a file so other capabilities can use it.

  3. 03

    Analyze sentiment

    Use this to check the sentiment of a document.

  4. 04

    Answer question

    This capability lets your agent answer questions by looking at a specific source document.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 19 available through Gradient AI.

  1. 05

    Complete model

    This capability generates a text completion based on your prompt.

  2. 06

    Create model

    Use this to start a new fine-tuned model instance.

  3. 07

    Create rag collection

    This capability sets up a new collection for RAG operations.

  4. 08

    Create transcription

    Use this to start a new audio transcription job.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 19 available through Gradient AI.

  1. 09

    Delete model

    This capability removes a fine-tuned model from your workspace.

  2. 10

    Extract entity

    Use this to pull structured data from a document using a schema.

  3. 11

    Extract PDF

    This capability pulls text and data out of a PDF file.

  4. 12

    Fine tune model

    Use this to train a model using the samples you provide.

Capability set04 / 05

13-16

4 capabilities in this set.

Part of 19 available through Gradient AI.

  1. 13

    Generate embeddings

    Use this to turn text into high-dimensional vectors.

  2. 14

    Get model

    This capability retrieves specific details about a model in your workspace.

  3. 15

    Get transcription

    Get the results of a transcription job once it finishes.

  4. 16

    List embeddings

    This capability shows you which models are available for generating embeddings.

Capability set05 / 05

17-19

3 capabilities in this set.

Part of 19 available through Gradient AI.

  1. 17

    List models

    Use this to see all your foundational and fine-tuned models.

  2. 18

    List rag collections

    This capability lists every RAG collection currently in your workspace.

  3. 19

    Summarize document

    This capability creates a summary of a provided document.

Real work

What teams actually run

01

Custom Model Iteration

An engineer fine-tunes a model on niche data and immediately tests its completions.

02

Automated Data Extraction

A developer uploads a PDF and uses the agent to extract structured entities.

03

RAG Pipeline Setup

A data scientist creates a RAG collection and generates embeddings for a knowledge base.

04

Sentiment Monitoring

An analyst runs sentiment analysis on large batches of text documents.

Automate a task

Put Gradient AI 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

Gradient AI 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 Gradient AI 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

1057ms average. Fast in production.

Gradient AI is checked daily against the live service.

Daily averagePeak 1267ms
Oct 3Today
Fastest day
880ms
Slowest day
1267ms
14-day trend
Slowing+7%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 19 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 Gradient AI, so you can see the experience inside your AI.

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

Gradient AI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_KwJfHerXBfsWKXVQH8bGJG4HGUwUfVlRXkPpGPNU/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 — Gradient AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "gradient-ai-llm-api-finetuning-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_KwJfHerXBfsWKXVQH8bGJG4HGUwUfVlRXkPpGPNU/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 Gradient AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Gradient AI owners hand off.

This MCP is built for technical users who need to bridge the gap between raw LLM infrastructure and their local development capabilities.

  • 01

    AI Engineers

    They use the MCP to iterate on fine-tuning experiments and test completions.

  • 02

    Data Scientists

    They use it to generate embeddings and run NLP analysis without local setups.

  • 03

    Developers

    They use it to add advanced LLM features to their apps via their agent.

FAQ

Questions Gradient AI owners ask.

  • 01

    How do I connect this MCP to my AI client?

    You subscribe to the MCP on Vinkius and connect your client once. After that, the capabilities are ready to use in Claude, Cursor, or Windsurf.

  • 02

    What credentials do I need?

    You will need your Gradient API Key and your Workspace ID to authenticate the connection.

  • 03

    Can I use my own fine-tuned models?

    Yes, you can list, create, and manage your custom fine-tuned model instances through the MCP.

  • 04

    Does this support RAG?

    Yes, you can create RAG collections and generate embeddings for retrieval tasks.

  • 05

    Can I process PDF files?

    Yes, the MCP includes capabilities to upload files and extract text or data from PDFs.

  • 06

    How can I start training a custom model with my own data?

    You can use the fine_tune_model capability. Simply provide the model ID and an array of training samples. The agent will handle the submission to Gradient's training infrastructure.

  • 07

    Can I use RAG (Retrieval Augmented Generation) with this server?

    Yes! The complete_model capability includes an optional rag parameter, allowing you to provide context or collection IDs to ground the model's responses in specific data.

  • 08

    How do I generate vector embeddings for my documents?

    Use the generate_embeddings capability by specifying a model slug (like 'bge-large') and a list of text inputs. It will return the high-dimensional vectors for your text.

Explore

More in Developer Tools

Suggestions

Connect Gradient AI to Claude, Cursor, ChatGPT & more