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

Q: How does the agent handle document summarization?

The agent calls summarizedocument to generate a concise summary of a file. It then runs personalizedocument to tailor that summary for a specific audience.

Q: How does Gradient AI (LLM API & Finetuning) secure training datasets and model weights in Pydantic AI?

All file uploads via uploadfile and training tasks run directly on Gradient's secure servers. The connection is handled via an ephemeral V8 sandbox on Vinkius. Your API keys and data payloads are never written to persistent disk on our platform.

Build type-safe fine-tuning and search pipelines using Pydantic AI to validate every model output.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate structured data extraction

The `extract_entity` tool pulls structured data out of raw documents based on a strict schema. When paired with Pydantic AI, the extracted data is immediately validated against your Python type models. If the model returns malformed fields, the framework catches it instantly. This MCP Server ensures your raw text parsing is reliable. Your agent can then use `extract_pdf` to re-parse the source document and try again, ensuring your database never receives corrupted data.

Control custom models safely with Pydantic AI

The `create_model` tool initiates a new fine-tuned model instance directly from your code. Your agent uploads clean training data using `upload_file` and executes `fine_tune_model` to train the weights. To keep your workspace clean, the agent uses `list_models` to identify stale models and `delete_model` to remove them. Every step of this lifecycle is validated, preventing accidental deletion of active models.

Type-safe vector search and generation

The `generate_embeddings` tool runs inside the MCP Server to create vector representations of your text inputs. Your agent stores these vectors in a collection created via `create_rag_collection`. When querying the collection, the agent uses `answer_question` to pull context. The response is validated against your Pydantic models, guaranteeing that the answers match your application's expected structure.

Setup guide

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

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gradient-ai-llm-api-finetuning-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Gradient AI (LLM API & Finetuning) tools.",
)

result = await agent.run("List recent Gradient AI (LLM API & Finetuning) transactions")
print(result.output)

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 Pydantic AI

Initialize the toolset class with your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets argument of your agent constructor.

Yes. Pydantic AI is model-agnostic. You can use any supported LLM to drive the agent while it calls Gradient tools like `complete_model` or `fine_tune_model` for specialized tasks.

The framework raises a validation error immediately. Your agent can catch this error and automatically prompt the model to correct the specific fields.

The agent calls `summarize_document` to generate a concise summary of a file. It then runs `personalize_document` to tailor that summary for a specific audience.

All file uploads via `upload_file` and training tasks run directly on Gradient's secure servers. The connection is handled via an ephemeral V8 sandbox on Vinkius. Your API keys and data payloads are never written to persistent disk on our platform.

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