How to Use the JSON Path Query Engine MCP in Google ADK

Q: How do I use the JSON Path Query Engine with a Google ADK agent?

You instantiate an McpToolset with the server's URL and pass it into your LlmAgent's tool list. The agent can then invoke the queryjson tool to extract data from JSON strings using JSONPath expressions.

Query massive JSON blobs from BigQuery before they hit your Google ADK agent's long-context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JSON Path Query Engine MCP to Google ADK

Create your Vinkius account to connect JSON Path Query Engine 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 JSON Path Query Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pre-filter Data for Gemini

Use the `query_json` tool to shrink massive JSON payloads down to size. Your Gemini agent can hold a million tokens, but you don't want to waste them on irrelevant data. This tool extracts just the fields you need using a standard JSONPath query. This is perfect for data pulled from BigQuery or other Google Cloud services. Instead of passing a huge result set to your Google ADK agent, you run a `query_json` operation first. The agent gets a clean, minimal input to work with.

Connects Directly to your LlmAgent

Integrating this MCP Server is straightforward. You wrap the server endpoint in an `McpToolset` and pass it directly to your `LlmAgent`'s `tools` parameter. There's no complex setup. You can even use the `tool_names` filter in the `McpToolset` to explicitly expose only the `query_json` tool. This gives you fine-grained control over what the agent can do, which is critical in enterprise environments.

Offload Parsing from Vertex AI

Let the MCP Server handle the expensive work of parsing and filtering. Running `query_json` on the Vinkius infrastructure keeps your own Vertex AI instances focused on reasoning, not data-munging. The server is built to handle large payloads without crashing. This is a more reliable approach than writing custom Python parsers that might run out of memory when a query from BigQuery returns an unexpectedly large JSON object.

Setup guide

Set up JSON Path Query Engine 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 JSON Path Query Engine 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="JSON Path Query Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to JSON Path Query Engine 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 jsonpath-plus. 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 JSON Path Query Engine 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 JSON Path Query Engine MCP in Google ADK

You instantiate an `McpToolset` with the server's URL and pass it into your `LlmAgent`'s tool list. The agent can then invoke the `query_json` tool to extract data from JSON strings using JSONPath expressions.

Yes. If you have a large JSON file in GCS, your agent can read the file content and pass it to the `query_json` tool. The tool will then extract the specific parts you need before your agent processes it.

Absolutely. It's designed for that exact scenario. When BigQuery returns a complex JSON structure, use `query_json` to pull out the key metrics or records before feeding them to your Gemini model.

It simplifies your agent's logic and saves on token costs. By pre-filtering data with an MCP tool, your agent gets a clean, predictable input, and you don't waste your model's large context window on junk data.

This server only sees the raw JSON string and the JSONPath query for each call. Each operation is isolated in a sandboxed environment on Vinkius. Your data isn't stored, logged, or used for anything beyond executing that single query.

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