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

Q: How does the agent handle audio files?

The agent uses createtranscription to start an asynchronous audio transcription job. It then polls gettranscription until the text is ready to be analyzed.

Q: Can my agent list all available fine-tuned models?

Yes. The agent calls listmodels to get a list of all custom and foundational models. It can then dynamically select the best model for the task.

Q: Where does Gradient AI (LLM API & Finetuning) process training data when configured with Google ADK?

Your raw PDFs and training files uploaded via uploadfile are sent directly to Gradient's secure cloud infrastructure. The MCP Server runs in an isolated, zero-trust V8 sandbox on Vinkius. No files or model weights are cached or stored on the Vinkius platform.

Ground your long-context Gemini agents with the Gradient AI (LLM API & Finetuning) MCP Server using the Google ADK.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Train custom models on enterprise data

The `fine_tune_model` tool trains custom weights using your specialized enterprise datasets. You upload training files using `upload_file` and initiate the training run with `create_model`. Your Gemini agent monitors the training progress via `get_model`. Once the training run finishes, the agent points its inference calls to the new model ID using `complete_model` to generate highly accurate domain-specific text.

Analyze heavy document workloads using this MCP Server

The `extract_pdf` tool parses heavy PDF documents and extracts raw text for your agent. The agent then runs `summarize_document` to condense massive files down to their core facts. To make the output match your target audience, the agent calls `personalize_document` to rewrite the summary. This works well for turning technical PDF data into executive summaries or client-facing notes.

Build vector search pipelines

The `create_rag_collection` tool builds indexed vector spaces directly from your agent's workspace. Your agent uses `generate_embeddings` to convert raw text strings into vector formats. When users query your data, the agent runs `answer_question` against the collection to pull context-aware answers. You can check your active vector indexes at any time using `list_rag_collections`.

Setup guide

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

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Gradient AI (LLM API & Finetuning) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Gradient AI (LLM API & Finetuning)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gradient AI (LLM API & Finetuning) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the toolset class from the ADK package. Pass your Vinkius HTTP endpoint into the streamable server parameters and feed the toolset to your agent.

Yes. Use the optional tool names filter when initializing your toolset. This lets you expose only specific tools like `complete_model` or `extract_entity` while hiding administrative tools.

The agent uses `create_transcription` to start an asynchronous audio transcription job. It then polls `get_transcription` until the text is ready to be analyzed.

Yes. The agent calls `list_models` to get a list of all custom and foundational models. It can then dynamically select the best model for the task.

Your raw PDFs and training files uploaded via `upload_file` are sent directly to Gradient's secure cloud infrastructure. The MCP Server runs in an isolated, zero-trust V8 sandbox on Vinkius. No files or model weights are cached or stored on the Vinkius 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