How to Use the Jestor MCP in Google ADK

Q: How do I configure the Jestor toolset within the Google ADK?

First, run pip install google-adk to get the library. Then, instantiate McpToolset using StreamableHttpServerParameters pointing to your Vinkius URL, and pass that toolset object into your LlmAgent constructor.

Q: How do I audit the automated workflows that my Gemini agent triggers?

You can have the agent run listworkflows to see what automation logic is active in your account. This allows the model to explain to users what background processes will run when a record is updated.

Connect Gemini agents to Jestor to run deep reasoning over your operational data alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jestor MCP to Google ADK

Create your Vinkius account to connect Jestor 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 Jestor with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context reasoning over Jestor database schemas

Google ADK lets you use Gemini's massive 1M+ token context window to analyze your entire business structure. By exposing `list_objects` and `get_object` to the model, your agent can map out every table and relationship in your account. It can digest thousands of lines of schema data in a single turn, giving it a complete picture of your setup. This is incredibly useful when you need to audit complex relational databases. Instead of writing custom documentation, the agent queries the live schema directly. It can then cross-reference this structure with your enterprise data pipelines in Google Cloud.

Filter specific Jestor MCP Server tools for enterprise security

Enterprise deployments require strict boundaries on what an agent can see and do. Google ADK allows you to pass a `tool_names` filter directly to your `McpToolset` configuration. This lets you explicitly whitelist safe tools like `list_records` and `get_record` while completely hiding administrative endpoints. If an agent does not need to audit system logic, simply omit `list_workflows` and `list_webhooks` from the allowed list. This reduces the risk of accidental actions and keeps the model focused on its specific task. It is a simple way to enforce least-privilege access at the application layer.

Bridge Google Cloud data with your operational workflows

Many teams keep their analytical data in BigQuery but run their daily operations on Jestor. Using this MCP Server with the Google ADK lets you build agents that bridge this gap. An agent can query historical trends in Vertex AI, then use `list_dashboards` to find where to write back the operational updates. This setup runs over both Stdio and HTTP transports depending on how you deploy your agent. You get a direct line from your Google Cloud infrastructure straight into your operational tables. It eliminates the need for brittle, custom-coded sync scripts.

Setup guide

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

First, run `pip install google-adk` to get the library. Then, instantiate `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius URL, and pass that toolset object into your `LlmAgent` constructor.

Yes, you can pass multiple toolsets to your Gemini agent. The agent can fetch operational records using `list_records` and join that data with analytical queries from your BigQuery tools within its large context window.

The ADK is highly flexible and supports both transport styles. You can connect to the hosted Vinkius server over HTTP using streamable parameters, or run the server locally in a container using Stdio transport during development.

You can have the agent run `list_workflows` to see what automation logic is active in your account. This allows the model to explain to users what background processes will run when a record is updated.

The MCP Server runs inside a secure, isolated V8 sandbox on Vinkius, which acts as a zero-trust barrier. Your database records fetched via `get_record` are only passed to the Gemini API over encrypted transit, and Vinkius never stores your underlying data payloads.

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