How to Use the JSON Merge Patch MCP in Google ADK

Apply surgical JSON Merge Patch updates within Google ADK to keep Gemini's long-context reasoning fast and accurate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JSON Merge Patch MCP to Google ADK

Create your Vinkius account to connect JSON Merge Patch 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 Merge Patch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct BigQuery Context Updates in Google ADK

The `apply_patch` tool executes precise RFC 7396 delta updates on large JSON fields fetched from BigQuery. Instead of writing heavy SQL update scripts or replacing entire rows, your Google ADK agent modifies only the necessary nested keys. This approach keeps database write-locks brief and prevents high-concurrency collisions in your Google Cloud infrastructure. Because Gemini can handle massive token windows, feeding it only the delta via this MCP Server keeps its reasoning loop focused on actual changes rather than redundant schema boilerplate.

Optimize Gemini Token Usage with Delta Patches

The `apply_patch` tool minimizes the context size your Google ADK agent needs to track when managing complex application states. Instead of feeding a massive 100,000-line JSON config into the prompt, the agent generates and applies a tight patch payload. This saves significant latency when using Gemini models over long-running task executions. The tool takes the original string and the patch string, returning the updated object deterministically without relying on the LLM to rewrite the file itself.

Limit Exposed Tools via Google ADK McpToolset

The `apply_patch` tool can be isolated using the tool_names filter when initializing your Google ADK toolset. This ensures your enterprise agent only has access to surgical JSON modifications and cannot execute unauthorized file operations. By restricting the agent to this single deterministic MCP tool, you eliminate the risk of accidental data deletion. The agent can update configuration states safely without needing full write permissions to the underlying storage buckets.

Setup guide

Set up JSON Merge Patch 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 Merge Patch 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 Merge Patch_agent",
    model="gemini-2.0-flash",
    instruction="You have access to JSON Merge Patch 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 JSON Merge Patch. 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 Merge Patch 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 Merge Patch MCP in Google ADK

Initialize the McpToolset using the streamable HTTP server parameters pointing to the Vinkius endpoint. Pass this toolset directly to your LlmAgent to let Gemini invoke apply_patch during its run.

While RFC 7396 handles the merge logic deterministically, your Google ADK agent must manage database-level locks. The apply_patch tool operates in-memory to resolve the delta, so you should write the output back to your cloud database using transaction blocks.

Yes, you can control this by wrapping the agent's system instructions to only allow apply_patch on designated file targets. This keeps your Google ADK agent focused on surgical modifications rather than general file alterations.

Gemini generates the patch based on the target schema you describe in its prompt. The apply_patch tool then parses and applies that patch, throwing an error if the model generates invalid JSON.

Your BigQuery JSON data payloads are processed within ephemeral, zero-trust V8 isolates on Vinkius. This MCP Server ensures your Google Cloud credentials and database strings never touch external disks and are discarded immediately after the patch execution.

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