How to Use the TrueFoundry MCP in Google ADK

Q: Can I list all available services with TrueFoundry and Google ADK?

You use truefoundrylistmcpservers to get a registry mapping of every logical MCP Tool in TrueFoundry. This gives your agent visibility into the entire toolset.

Q: What deployment status can I check with TrueFoundry and Google ADK?

You call truefoundrygetdeploymentstatus to emit detailed metric states on the orchestration matrix bounds. This confirms service availability before your agent attempts to use it.

Q: Does TrueFoundry support multiple model queries with Google ADK?

Yes, truefoundryrungatewaychat explicitly handles passing a model query string through the gateway. This ensures your Gemini-powered agent can talk to various underlying models.

Build enterprise agents with the Google ADK. Connect Gemini reasoning directly to infrastructure services.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrueFoundry MCP to Google ADK

Create your Vinkius account to connect TrueFoundry 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 TrueFoundry with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Listing Models on the MCP Server

The `truefoundry_list_gateway_models` tool lists all accessible foundation models from the TrueFoundry unified AI gateway. This is useful when your Google ADK agent needs to choose between different Gemini or Vertex AI endpoints. It gives you a complete map of every proxy model available, allowing for targeted long-context reasoning within your enterprise architecture.

Executing Chat with the MCP Server

Use `truefoundry_run_gateway_chat` to pass an explicit query string through TrueFoundry. This executes a model call that the Google ADK agent can interpret, especially when acting on data from BigQuery. This function acts as the primary conduit for running reasoning tasks across 1M+ token contexts.

Inspecting Tool Schemas

To ensure correctness before execution, you extract the exact JSON metadata of any registered TrueFoundry tool schema using `truefoundry_get_mcp_server_info`. This is key for building robust agents that interact with enterprise data. It's a validation step; your ADK agent reads this structure to guarantee it calls the service correctly.

Setup guide

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

The TrueFoundry MCP Server provides model access and deployment tools that your agent uses to process structured data. It allows the agent to run complex reasoning tasks on information sourced from BigQuery.

You use `truefoundry_list_mcp_servers` to get a registry mapping of every logical MCP Tool in TrueFoundry. This gives your agent visibility into the entire toolset.

You call `truefoundry_get_deployment_status` to emit detailed metric states on the orchestration matrix bounds. This confirms service availability before your agent attempts to use it.

Yes, `truefoundry_run_gateway_chat` explicitly handles passing a model query string through the gateway. This ensures your Gemini-powered agent can talk to various underlying models.

The server touches model schema JSON metadata. This definition dictates how your agents interact with external services, which is crucial for maintaining enterprise governance when working with BigQuery.

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