How to Use the LiteLLM (LLM Proxy & Spend Tracking) MCP in Google ADK

Control your MCP Server routes and track team API budgets directly from your Google ADK enterprise pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiteLLM (LLM Proxy & Spend Tracking) MCP to Google ADK

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Your MCP Server Safely Inside Google ADK

Large-context reasoning with Gemini can quickly run up costs. This server lets your Google ADK agent query `get_team_info` and `get_user_info` to monitor exactly how many tokens your BigQuery analysis pipelines are consuming. By setting strict boundaries using `create_team`, you prevent runaway costs during deep-reasoning cycles. Your agent checks limits before executing multi-million token context windows.

Dynamic Vertex and Bedrock Route Management

Keep your hybrid cloud models aligned. This MCP Server lets your Google ADK agent inject fresh routing endpoints using `create_model` and clean up dead deployments with `delete_model` without requiring manual redeploys. When your pipeline detects latency spikes in Vertex AI, the agent queries `get_model_info` to find alternative routes. It then shifts the workload to backup endpoints instantly.

Automate Key Provisioning for Cloud Workflows

Scale your enterprise agent fleets securely. Your Google ADK agent calls `generate_key` to provision unique API credentials for specific departments, then cleans them up with `delete_key` when jobs finish. This automation integrates with your Google Cloud IAM policies. Instead of sharing master keys, each sub-agent gets its own scoped credential with limits tracked via `get_key_info`.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) 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="LiteLLM (LLM Proxy & Spend Tracking)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM. 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 LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) MCP in Google ADK

Initialize McpToolset using your Vinkius HTTP transport URL. Pass this toolset into your LlmAgent constructor to expose the gateway tools to your Gemini models.

Yes, Gemini's long-context capability allows it to analyze complex routing tables returned by `get_model_info`. The model can make highly informed decisions on when to execute `generate_key` or `delete_model`.

Yes, the MCP Server supports both Stdio and HTTP transports. You pass the server parameters to StreamableHttpServerParameters to establish a secure, persistent connection.

Yes, you can use the optional tool names filter in the ADK toolset configuration. This allows you to restrict the agent to read-only tools like `get_key_info` while blocking destructive tools like `delete_key`.

The server only interacts with your LiteLLM gateway admin API to manage keys and budgets. Your raw Google Cloud credentials and BigQuery datasets are never touched or processed by this connection.

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