How to Use the LibreTranslate API MCP in Google ADK

Q: How do I connect the LibreTranslate API to a Google ADK agent?

Use the McpToolset class with StreamableHttpServerParameters pointing to your endpoint. Pass the toolset into the tools parameter of your LlmAgent.

Q: Can I restrict which tools the Google ADK agent can access?

Yes. Use the toolnames filter in your McpToolset configuration to expose only translatetext or detectlanguage depending on the agent's role.

Q: How does the agent handle large translation payloads?

The agent splits long text into chunks and calls translatetext iteratively, leveraging Gemini's long-context window to keep track of the overall narrative.

Translate millions of database rows inside your Google ADK pipelines using local translation tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LibreTranslate API MCP to Google ADK

Create your Vinkius account to connect LibreTranslate API 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 LibreTranslate API with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Translate BigQuery data with Google ADK

Large datasets in Google Cloud often contain mixed-language feedback. This MCP Server allows your Google ADK agents to pull raw text from BigQuery, detect the source via `detect_language`, and write translated outputs back to your database. You don't need to write custom translation cloud functions. The agent calls `translate_text` directly within its reasoning loop, processing thousands of rows without leaving your secure cloud environment.

Long-context translation processing

Gemini models handle massive token limits, but translating huge documents still requires structured tools. Use `translate_text` to process document blocks while maintaining the original context in the model's memory. Before starting a heavy job, the agent runs `check_api_status` to confirm your translation server is ready for the load. This keeps your Google ADK pipelines running smoothly on your MCP setup.

Dynamic language filtering for enterprise agents

Enterprise deployments need strict control over which languages are permitted. Your agent calls `list_supported_languages` to verify incoming payloads against your authorized list before initiating any translation tasks. This step prevents your Google ADK agent from wasting API credits on unsupported dialects. By filtering inputs early, you maintain high throughput and avoid processing errors.

Setup guide

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

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your endpoint. Pass the toolset into the `tools` parameter of your `LlmAgent`.

Yes. Use the `tool_names` filter in your `McpToolset` configuration to expose only `translate_text` or `detect_language` depending on the agent's role.

Yes. This MCP Server supports both HTTP and Stdio transports, giving you flexibility in how you deploy your agent containers on Google Cloud.

The agent splits long text into chunks and calls `translate_text` iteratively, leveraging Gemini's long-context window to keep track of the overall narrative.

Your source text strings and translated outputs are transmitted directly between your Google Cloud environment and your LibreTranslate endpoint. Vinkius handles the connection token securely without inspecting or logging the payload content.

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