How to Use the JSONPlaceholder MCP in Google ADK

Q: How do I configure JSONPlaceholder with Google ADK?

Install the google-adk package. Initialize an McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset to your LlmAgent constructor.

Q: Can I restrict which JSONPlaceholder tools my Google ADK agent sees?

You can. Use the toolnames filter when setting up the McpToolset. This lets you expose read-only tools like getphoto while hiding write tools like deletepost.

Q: What happens when the agent tries to delete a post?

The deletepost tool simulates a successful DELETE request and returns an empty response object. Your agent logic will register a success, allowing you to test error handling and success states safely.

Feed mock REST API data from an MCP Server into Google ADK to test your Gemini agents before touching enterprise infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JSONPlaceholder MCP to Google ADK

Create your Vinkius account to connect JSONPlaceholder 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 JSONPlaceholder with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mock enterprise data pipelines in Google ADK

This JSONPlaceholder MCP server provides a fake REST API so your Gemini agents can practice fetching and manipulating data. Instead of pointing an untested agent at your live BigQuery tables, you let it practice on mock data. It can run `list_users` or `get_user_todos` to simulate pulling records from an external system. You load the tools into your `LlmAgent` using the `McpToolset` class. The setup supports both Stdio and HTTP transports. If you only want the agent to read data, you can use the `tool_names` filter to expose just `get_post` and `list_albums`, hiding the write tools entirely.

Test 1M+ token context windows

Gemini models handle massive context windows, and you need to verify your agent actually uses that context. You can instruct the agent to run `list_posts`, `list_comments`, and `list_photos` in sequence, dumping hundreds of mock JSON records into its context. Once the context is loaded, you ask the agent to find specific correlations. Have it match an album ID from `get_album_photos` to a user ID. This proves your agent can retain and reason over large volumes of fetched API data without losing track of the original request.

Simulate complex agent workflows

Enterprise agents rarely just read data; they usually have to act on it. You can build a workflow where the agent finds a specific user via `get_user`, reads their tasks with `get_user_todos`, and then generates a summary report. To test the write path, the agent can call `create_post` to log its findings. The mock API accepts the payload and returns a 201 Created status. This lets you validate the entire read-analyze-write pipeline inside Google Cloud before you swap the mock server for your actual production endpoints.

Setup guide

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

Install the `google-adk` package. Initialize an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass this toolset to your `LlmAgent` constructor.

You can. Use the `tool_names` filter when setting up the `McpToolset`. This lets you expose read-only tools like `get_photo` while hiding write tools like `delete_post`.

Yes. You can have the agent fetch massive amounts of mock data using `list_comments` or `list_todos`. The Gemini model will hold all that JSON in its context window for complex reasoning tasks.

The `delete_post` tool simulates a successful DELETE request and returns an empty response object. Your agent logic will register a success, allowing you to test error handling and success states safely.

The server exclusively processes synthetic data like placeholder album titles, fake user emails, and dummy task lists. Vinkius runs the tool execution inside a zero-trust, ephemeral sandbox that vanishes the millisecond the HTTP response completes.

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