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

Q: How do I add Gradient AI (LLM API & Finetuning) to my Cursor project?

Create a .cursor/mcp.json file in your project root. Add the MCP Server configuration under the mcpServers key, then enable Agent mode in your editor chat.

Q: Can I use Gradient AI (LLM API & Finetuning) to generate embeddings for my codebase in Cursor?

Yes. The agent calls generateembeddings to convert your source files into vector representations, allowing for semantic code search.

Q: Does Gradient AI (LLM API & Finetuning) support automatic entity extraction in Cursor?

Yes, it does. Your agent can execute extractentity on your workspace files to generate structured JSON schemas directly inside your editor.

Generate code using custom fine-tuned model outputs directly inside the Cursor editor.

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 Cursor

Create your Vinkius account to connect Gradient AI (LLM API & Finetuning) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject custom model completions into your Cursor code

Cursor lets your agent write code based on real-time model outputs rather than static mock data. By calling `complete_model` directly from the editor, your agent pulls predictions from your fine-tuned models to write highly accurate, domain-specific code. You can list your custom models using `list_models` or query a specific model's metadata with `get_model`. This ensures the code your editor generates matches the exact schema of your active model deployments.

Build RAG-backed codebases with this MCP Server

Stop guessing which internal APIs or documentation files you need to reference. Your agent uses `create_rag_collection` to index your local repository files and `list_rag_collections` to locate existing knowledge bases. When writing code, the editor calls `generate_embeddings` to find relevant internal code snippets. It then runs `answer_question` to feed the exact context directly into your active editor buffer.

Train models on your workspace files

You can train models without leaving your development workspace through this MCP Server. Your agent packages your local code files, sends them using `upload_file`, and initiates training with `fine_tune_model`. If you need to clean up old experiments, the agent can call `delete_model` to remove outdated weights. This keeps your active workspace clean and prevents you from paying for abandoned model instances.

Setup guide

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

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Gradient AI (LLM API & Finetuning) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Gradient AI (LLM API & Finetuning) transactions." If the MCP tools are loaded correctly, Cursor will call the Gradient AI (LLM API & Finetuning) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "gradient-ai-llm-api-finetuning-mcp": {
      "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 Cursor

Create a `.cursor/mcp.json` file in your project root. Add the MCP Server configuration under the `mcpServers` key, then enable Agent mode in your editor chat.

Yes. The agent calls `generate_embeddings` to convert your source files into vector representations, allowing for semantic code search.

Yes, it does. Your agent can execute `extract_entity` on your workspace files to generate structured JSON schemas directly inside your editor.

Yes, because the agent runs the tools in your active session, you can prompt it to execute `complete_model` and output the results directly into your terminal or file.

All code files and vector embeddings are securely sent to Gradient's API via SSL. The MCP Server runs inside a zero-trust, ephemeral V8 container, ensuring no local code is stored or exposed.

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

Vercel AI SDK sdk-typescript