How to Use the LibreChat MCP in Google ADK

Q: How do I load LibreChat tools into a Google ADK agent using MCP?

You initialize the McpToolset with your streamable HTTP server URL and pass it to the LlmAgent constructor. The toolset automatically runs listmodels to discover and register your LibreChat endpoints. Your Gemini models can then invoke them natively during reasoning cycles.

Q: Can Google ADK run LibreChat completions alongside BigQuery?

Yes, you can combine your BigQuery data tools and the chatcompletions tool in the same agent toolset. Your Gemini agent can query your database, analyze the raw data, and then send the formatted results to LibreChat.

Q: How does Google ADK handle LibreChat session expiration?

The login tool retrieves fresh access and refresh tokens whenever your connection starts. If a token expires during a long-running Google ADK pipeline, the toolset re-authenticates to maintain an active session.

Connect your enterprise Gemini agents to LibreChat using the Google ADK for context-rich data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LibreChat MCP to Google ADK

Create your Vinkius account to connect LibreChat 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 LibreChat with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute LibreChat completions with Google ADK

The `chat_completions` tool connects your Gemini models to specific LibreChat Agent IDs to handle long-context reasoning tasks. This allows your Google ADK agent to process massive document sets and send structured prompts directly to your chat backend. For rapid, single-turn text generation, the `open_responses` tool bypasses heavy agent steps to deliver faster outputs to your Google ADK application.

Map models using this MCP Server

The `list_models` tool pulls the entire registry of available engines and custom agents from your LibreChat instance and exposes them to your Google ADK toolset array. Your Gemini agents can analyze this list to choose the best LibreChat backend model for a specific database query. This bridges the gap between your Google Cloud infrastructure and your custom chat templates through this MCP integration.

Inject session tokens into Google ADK pipelines

The `login` tool authenticates your Google ADK python scripts with your LibreChat server to generate secure access tokens. This prevents unauthorized access to your custom endpoints when running automated pipelines. The framework injects these LibreChat tokens into the HTTP transport headers automatically, ensuring your Google Cloud data pipelines run without manual credentials.

Setup guide

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

You initialize the `McpToolset` with your streamable HTTP server URL and pass it to the `LlmAgent` constructor. The toolset automatically runs `list_models` to discover and register your LibreChat endpoints. Your Gemini models can then invoke them natively during reasoning cycles.

Yes, you can combine your BigQuery data tools and the `chat_completions` tool in the same agent toolset. Your Gemini agent can query your database, analyze the raw data, and then send the formatted results to LibreChat.

The `login` tool retrieves fresh access and refresh tokens whenever your connection starts. If a token expires during a long-running Google ADK pipeline, the toolset re-authenticates to maintain an active session.

Yes, you can pass a specific list of tool names to your toolset configuration. For example, you can expose only `chat_completions` while hiding administrative tools like `login`.

Your tokens and model lists are processed in an isolated V8 sandbox on Vinkius. They are never logged or stored on disk, and they transfer directly to your Google Cloud environment. This keeps your instance credentials completely isolated from external tracking.

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