How to Use the LeanCloud MCP in Google ADK

Q: How do I register the LeanCloud MCP Server tools in Google ADK?

Instantiate McpToolset with your Vinkius HTTP URL. Then, pass that toolset object into the tools array when initializing your LlmAgent.

Q: Can Gemini analyze files stored in LeanCloud using Google ADK?

Yes. Your agent can run listfiles to retrieve metadata, then download the target files to feed them directly into Gemini's multimodal context window for processing.

Q: Can I restrict agents from modifying specific database classes?

Yes, you can use the toolnames filter in Google ADK to exclude tools like updateobject or createobject entirely from the agent's action space.

Q: Where are my application statistics processed?

Your application statistics from getappstats and database objects are fetched from LeanCloud, routed through the MCP Server secure proxy, and processed within your Google Cloud project boundary. No raw database rows are stored on Vinkius servers.

Feed massive LeanCloud datasets into Gemini long-context windows using Google ADK to analyze backend operations at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LeanCloud MCP to Google ADK

Create your Vinkius account to connect LeanCloud 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 LeanCloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise data synthesis with Google ADK

Large-scale LeanCloud backends generate massive amounts of relational data that Google ADK agents must process using `list_objects`. By feeding `list_objects` output via this MCP Server into Gemini's million-token context window via Google ADK, your agents can run deep trend analysis on your LeanCloud databases without pagination headaches. You can combine this raw LeanCloud database pull with your existing BigQuery pipelines using Google ADK. The Google ADK handles the flow, letting Gemini analyze your LeanCloud app performance metrics alongside enterprise warehouse data.

Automated push campaigns and user segmentation

Target your LeanCloud users based on actual database activity using Google ADK and `list_users`. This LeanCloud MCP Server exposes `list_users` and `get_user` to your Gemini agents, allowing Google ADK to segment cohorts based on signup dates or usage patterns. Once the segments are defined, the Google ADK agent can trigger targeted alerts via `push_notification` to LeanCloud devices. The entire process runs autonomously within your Google Cloud infrastructure, keeping LeanCloud marketing workflows close to your data.

Strict tool filtering for secure LeanCloud administration

Enterprise security requires limiting what a Google ADK agent can do to your production LeanCloud database, especially when using `delete_object`. Google ADK allows you to apply a `tool_names` filter to the LeanCloud toolset, ensuring the agent cannot execute destructive tools like `delete_object`. Our custom agent retains access to safe read-only LeanCloud operations like `get_app_stats` and `list_files`. This setup protects your LeanCloud backend from unauthorized modifications while still providing full observability to your Google ADK pipelines.

Setup guide

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

Instantiate `McpToolset` with your Vinkius HTTP URL. Then, pass that toolset object into the `tools` array when initializing your `LlmAgent`.

Yes. Your agent can run `list_files` to retrieve metadata, then download the target files to feed them directly into Gemini's multimodal context window for processing.

Gemini's large context window allows you to pull large batches of records using `list_objects`. However, you should still implement chunking to avoid hitting LeanCloud's maximum response payload limits.

Yes, you can use the `tool_names` filter in Google ADK to exclude tools like `update_object` or `create_object` entirely from the agent's action space.

Your application statistics from `get_app_stats` and database objects are fetched from LeanCloud, routed through the MCP Server secure proxy, and processed within your Google Cloud project boundary. No raw database rows are stored on Vinkius servers.

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