How to Use the Deep Diff Engine MCP in Google ADK

Compare massive JSON objects from BigQuery with your Google ADK agent. Get exact, structured diffs for enterprise-scale automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deep Diff Engine MCP to Google ADK

Create your Vinkius account to connect Deep Diff 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 Deep Diff Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Diff BigQuery JSON Without the Noise

Pull two large JSON documents from a BigQuery table and have your Google ADK agent find the differences. Instead of feeding multi-megabyte strings into a prompt, your agent invokes the `calculate_json_diff` tool. The agent gets back a concise report of what actually changed. It's faster, it costs less in tokens, and it's a hundred times more accurate than asking an LLM to spot differences in a huge blob of text.

Free Up Your Agent's Context Window

Even with Gemini's 1M+ token context, you don't want to waste it on solved problems. Diffing is a deterministic task. Offload it to this specialized MCP Server and save your agent's context for what it's good at: complex reasoning. Your agent can now use its full context to understand the business implications of a change, not the mechanical process of finding it. This leads to smarter, more capable agents.

Connect Agents to Vertex AI Pipelines

The structured output from `calculate_json_diff` is the perfect trigger for your Google Cloud infrastructure. An agent can get a diff, identify a critical change, and then kick off a formal Vertex AI Pipeline. This makes your agent a true part of your enterprise workflow. Use it to trigger data validation, model retraining, or incident response pipelines based on precise changes in your data.

Setup guide

Set up Deep Diff 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 Deep Diff 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="Deep Diff Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Deep Diff 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 deep-diff. 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 Deep Diff 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 Deep Diff Engine MCP in Google ADK

Have your agent periodically query a row, pull the JSON from a column, and compare it to a previous version using `calculate_json_diff`. The agent can then act on the specific changes reported by the tool, like logging them or triggering an alert.

The server is designed for large objects, but there are practical limits based on network transfer. It's built to handle the kind of complex JSON documents you'd find in enterprise systems, well beyond what's practical to put in a prompt.

Yes. It traverses the entire JSON structure. The output gives you the exact path to any changed element, no matter how deeply nested it is. This is critical for working with real-world enterprise data.

Accuracy and cost. This tool gives a guaranteed-correct result every time. Asking an LLM is slower, uses expensive tokens, and can make mistakes on complex objects. Use your agent for reasoning, not for running basic algorithms.

It's processed and immediately discarded. Your JSON inputs are handled in a temporary, isolated memory space for the sole purpose of the diff operation. Nothing is logged or stored on the MCP server.

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