How to Use the Lokalise MCP in Google ADK

Q: How does Google ADK handle large Lokalise files?

The agent uses uploadfile to send raw files up to the translation platform. Gemini's massive context window allows the agent to parse the file structure first, ensuring it only uploads valid schemas.

Q: Can I restrict which tools are exposed to my Gemini agent?

Yes, Google ADK supports a toolnames filter on the toolset. You can limit the agent's access to read-only tools like listkeys and getproject if you want to prevent automated writing.

Connect the Google ADK to Lokalise to automate enterprise translation pipelines using Gemini's long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lokalise MCP to Google ADK

Create your Vinkius account to connect Lokalise 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 Lokalise with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-Rich Enterprise Translation

The `add_translation` tool pushes context-matched strings directly into your localization projects. Google ADK uses Gemini's million-token context window to analyze entire source codebases alongside target translations. The agent processes massive files in a single pass, then uses `list_translations` to verify accuracy. It checks your existing translations to ensure the new strings match the tone of your enterprise brand.

Google ADK and MCP Server file syncing

The `upload_file` tool transfers source files from your local build environment directly to your translation dashboard using this MCP Server. Your agent monitors file changes and triggers this tool automatically. When translation jobs finish, the agent calls `download_file` to fetch the localized assets. This removes the manual exporting steps that typically slow down enterprise release cycles.

Project-Wide Auditing

The `list_projects` tool fetches all active localization projects associated with your enterprise account. The agent can scan every project to cross-reference translation coverage with data stored in BigQuery. Using `list_team_members` and `list_orders`, the agent audits who has access and tracks the progress of professional translation orders. It compiles these insights into reports that sync directly with your Vertex AI dashboard.

Setup guide

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

Instantiate McpToolset using the StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset into your LlmAgent configuration to expose the translation tools.

Yes, your agent can read product metadata from BigQuery and use create_key or update_key to build matching localization keys. This ensures your product catalog and translation keys stay aligned.

The agent uses upload_file to send raw files up to the translation platform. Gemini's massive context window allows the agent to parse the file structure first, ensuring it only uploads valid schemas.

Yes, Google ADK supports a tool_names filter on the toolset. You can limit the agent's access to read-only tools like list_keys and get_project if you want to prevent automated writing.

This MCP Server handles translation keys, localization files, and project metadata. All traffic passes through Vinkius's zero-trust gateway, which encrypts your API tokens in transit and executes the server in an isolated sandbox.

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