How to Use the Gradient AI (LLM API & Finetuning) MCP in Claude Code

Q: How do I connect Gradient AI (LLM API & Finetuning) to Claude Code?

Use the claude mcp add command in your terminal. Pass the server URL and transport flags to register the tools for use in your scripts.

Q: Is Gradient AI (LLM API & Finetuning) available in Claude Code for embeddings?

Yes, you can call generateembeddings directly from your command line. It's a reliable way to generate vector data for your production RAG pipelines.

Q: Can I perform fine-tuning with Gradient AI (LLM API & Finetuning) in Claude Code?

You can. By using finetunemodel within your shell scripts, you can fully automate the training process based on your local dataset files.

Q: How do I verify the server is running?

Run claude mcp list in your terminal. This command will show you the status of the server and confirm that all 19 tools are ready for use.

Run headless automation with Claude Code and the Gradient AI (LLM API & Finetuning) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gradient AI (LLM API & Finetuning) MCP to Claude Code

Create your Vinkius account to connect Gradient AI (LLM API & Finetuning) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Gradient AI (LLM API & Finetuning) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless model management

Use `create_model` and `delete_model` in your CI/CD scripts to manage your model lifecycle programmatically. It runs without any GUI intervention. This is perfect for automated testing pipelines where you need to spin up a fine-tuned model, run a validation suite, and tear it down.

Terminal-based RAG operations

Pipe your documentation into `create_rag_collection` from your shell. You can then use `answer_question` to query your docs directly from your terminal session. This keeps your workflow inside the CLI. You get precise answers without ever leaving your terminal or switching to a browser.

Batch document processing

Automate the summarization of large file sets using `summarize_document`. You can loop through files in your directory and pipe the output to a log file. It handles the heavy lifting of parsing and condensing your data, letting you focus on the output rather than the mechanics of the LLM call.

Setup guide

Set up Gradient AI (LLM API & Finetuning) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see gradient-ai-llm-api-finetuning-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Gradient AI (LLM API & Finetuning) transactions." It will automatically discover and invoke the available Gradient AI (LLM API & Finetuning) tools.

Terminal

claude mcp add --transport http gradient-ai-llm-api-finetuning-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Gradient AI (LLM API & Finetuning) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "gradient-ai-llm-api-finetuning-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Gradient AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Gradient AI (LLM API & Finetuning) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Gradient AI (LLM API & Finetuning) MCP in Claude Code

Use the `claude mcp add` command in your terminal. Pass the server URL and transport flags to register the tools for use in your scripts.

Yes, you can call `generate_embeddings` directly from your command line. It's a reliable way to generate vector data for your production RAG pipelines.

You can. By using `fine_tune_model` within your shell scripts, you can fully automate the training process based on your local dataset files.

The server uses a single endpoint token for authentication. All communication happens over a secure connection, and no data is stored on the server beyond the active session requirements.

Run `claude mcp list` in your terminal. This command will show you the status of the server and confirm that all 19 tools are ready for use.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python