How to Use the DummyJSON MCP in Google ADK

Q: How do I initialize the DummyJSON MCP Server inside Google ADK?

Install google-adk and configure McpToolset with the Vinkius HTTP URL. You then pass that toolset to your LlmAgent instance so your Gemini model can access all 61 endpoints.

Q: Can I use Google ADK to filter specific DummyJSON tools?

Yes, you can pass a list of allowed tool names to the McpToolset constructor. This limits the agent to specific actions like getcart and updatecart to save token overhead.

Q: How do Gemini's large context windows interact with mock tools?

Your agent can call listposts or listcomments and process the entire payload at once. Gemini's 1M+ token limit means it won't choke on large mock datasets returned by the server.

Q: Where does my mock user auth data go when using this setup?

Your simulated credentials and dummy JWTs from authlogin stay strictly within the ephemeral V8 sandbox. V8 isolates prevent any data sharing across runtimes.

Power your enterprise Gemini workflows with simulated store and user data using this Google ADK MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DummyJSON MCP to Google ADK

Create your Vinkius account to connect DummyJSON 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 DummyJSON with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context testing with Google ADK

This MCP Server delivers `list_products` and `list_users` to let your Google ADK agent pull entire DummyJSON datasets into Gemini. Gemini models have massive context windows, and these DummyJSON tools feed your Google ADK pipelines realistic data. You can feed raw outputs from DummyJSON tools like `list_recipes` directly into your Google ADK pipelines. Your Google ADK agent processes hundreds of DummyJSON mock records in a single turn, simulating complex data-crunching tasks.

Enterprise database simulation in Google ADK

This MCP Server provides `get_user_carts` and `get_user_todos` to mimic real customer profiles in Google ADK. Before writing code to touch BigQuery, test your Google ADK logic with these DummyJSON schemas. Your Google ADK agent gets realistic responses from DummyJSON tools like `search_users` and `get_product` without risking live database corruption. This approach lets you verify how your Google ADK agent handles nested DummyJSON structures.

State mutation testing in Gemini agents

This MCP Server exposes simulated mutation endpoints like `add_product` and `delete_comment` to test conditional branching in Google ADK. Track how your Google ADK agent handles writes by letting it call simulated DummyJSON mutation endpoints. Since these DummyJSON mutations are simulated, your Google ADK agent won't pollute any physical databases. You can verify if the Google ADK agent correctly calls the DummyJSON `update_user` tool after processing a simulated support ticket.

Setup guide

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

Install `google-adk` and configure `McpToolset` with the Vinkius HTTP URL. You then pass that toolset to your `LlmAgent` instance so your Gemini model can access all 61 endpoints.

Yes, you can pass a list of allowed tool names to the `McpToolset` constructor. This limits the agent to specific actions like `get_cart` and `update_cart` to save token overhead.

Yes, Google ADK handles both connection types natively. For cloud-deployed agents on Vertex AI, the streamable HTTP transport through Vinkius is the most reliable option.

Your agent can call `list_posts` or `list_comments` and process the entire payload at once. Gemini's 1M+ token limit means it won't choke on large mock datasets returned by the server.

Your simulated credentials and dummy JWTs from `auth_login` stay strictly within the ephemeral V8 sandbox. V8 isolates prevent any data sharing across runtimes.

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