How to Use the Metatext MCP in Google ADK

Q: Can Google ADK agents use Metatext to curate datasets?

Yes, your Google ADK agents can use createdatasetrecord to write processed data back to your training sets. This is perfect for distilling long-context Gemini outputs into smaller, specialized models.

Connect your Google ADK pipelines to this MCP Server to manage NLP models and datasets at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metatext MCP to Google ADK

Create your Vinkius account to connect Metatext 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 Metatext with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run high-throughput predictions inside Google ADK

This setup triggers the `run_model_inference` tool to execute predictions directly within your Google ADK agent loops. Your Gemini models can process massive context windows and send structured inputs to your deployed Metatext NLP models. The framework pipes the outputs back into your Google Cloud environment, making it easy to feed prediction results into BigQuery. This allows you to combine long-context reasoning with fast, specialized model execution.

Map BigQuery data to Metatext datasets

The integration uses `create_dataset_record` and `list_nlp_datasets` to sync your cloud data warehouses with your training sets. Your agent can read rows from BigQuery and format them into dataset records in real time. By calling `get_dataset_details` and `list_dataset_records`, the agent verifies that the records match your schema before writing. This keeps your training pipelines clean without requiring manual export steps.

Monitor model deployments from your MCP Server

The server exposes active deployments to your Gemini agent via `list_model_deployments` and `list_nlp_models`. Your agent can check which models are live before routing user queries. If a model isn't currently deployed, the agent can search for alternatives using `search_nlp_models` or pull specifications with `get_model_details`. This ensures your Google ADK workflows never hit dead ends due to missing endpoints.

Setup guide

Set up Metatext 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 Metatext 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="Metatext_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Metatext 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 Metatext. 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 Metatext 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 Metatext MCP in Google ADK

Initialize the toolset using the streamable HTTP parameters pointing to your Vinkius endpoint. Pass that toolset directly to your agent constructor to expose the dataset and inference tools.

Yes, your Google ADK agents can use `create_dataset_record` to write processed data back to your training sets. This is perfect for distilling long-context Gemini outputs into smaller, specialized models.

Yes, you can pass a list of specific tool names to the toolset parameters if you only want your agent to run inference. This limits the agent's access to tools like `run_model_inference` while hiding dataset modification tools.

Yes, the toolset supports both stdio and HTTP transports. For cloud-deployed Google ADK agents, the hosted HTTP option on Vinkius is the easiest way to connect your MCP Server without managing local processes.

Your Metatext API tokens are injected securely as environment variables in our sandboxed runtime. The server only handles the metadata returned by `list_model_deployments` over encrypted HTTPS, ensuring your infrastructure details remain private.

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