How to Use the Fxiaoke MCP in Google ADK

Q: How do I configure the Fxiaoke MCP Server with Google ADK?

Install google-adk via pip. Wrap your endpoint in StreamableHttpServerParameters and pass it to McpToolset. Feed that toolset to your LlmAgent and you are ready to go.

Q: Can Google ADK filter which MCP tools the agent sees?

Yes. You can use the toolnames filter to restrict access. If you only want an agent reading data, expose listaccounts and listcontacts, but hide the creation endpoints.

Q: Does Fxiaoke work with Gemini's long context window?

It works perfectly. You can pull massive payloads using listopportunities and Gemini processes the entire JSON structure without dropping details or hallucinating metrics.

Feed Fxiaoke sales data directly into Google ADK and let Gemini analyze your entire CRM pipeline in a single prompt.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fxiaoke MCP to Google ADK

Create your Vinkius account to connect Fxiaoke 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 Fxiaoke with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fxiaoke MCP Server for Google ADK

The Fxiaoke MCP Server dumps thousands of records from `list_opportunities` and `list_leads` straight into Gemini's massive context window. Gemini's 1M+ token capacity changes how you interact with CRM data. Connect the server using `McpToolset` and your agent reads the entire pipeline at once. You avoid chunking or vector databases entirely here. The agent reads the raw Fxiaoke output and cross-references it with your BigQuery datasets in real time. It finds patterns in your Chinese market data that human analysts miss.

Drive Actions from Vertex AI

Your Google Cloud agents can execute `create_lead` and `create_opportunity` directly from Vertex AI workflows. Reading data is fine, but writing it makes money. You build autonomous pipelines that react to market signals instantly. If a marketing campaign triggers a spike in interest, your agent parses the incoming signals and creates the Fxiaoke records automatically. No manual data entry required. Your sales team wakes up to a populated CRM.

Track Approvals and Sales Tasks

By calling `list_approvals` and `get_approval_details`, your Gemini agent monitors the exact state of every pending contract in the Chinese market. Bottlenecks kill deals. The agent flags stuck contracts before they cost you revenue. It can also pull `list_sales_tasks` to see what your reps are doing to unblock those deals. You get a complete picture of the sales floor without ever logging into the clunky Fxiaoke dashboard.

Setup guide

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

Install `google-adk` via pip. Wrap your endpoint in `StreamableHttpServerParameters` and pass it to `McpToolset`. Feed that toolset to your `LlmAgent` and you are ready to go.

Yes. You can use the `tool_names` filter to restrict access. If you only want an agent reading data, expose `list_accounts` and `list_contacts`, but hide the creation endpoints.

It works perfectly. You can pull massive payloads using `list_opportunities` and Gemini processes the entire JSON structure without dropping details or hallucinating metrics.

The tools handle pagination natively. Your agent will request the next page of results from `list_users` or `list_sales_tasks` until it has the complete dataset in memory.

We do not store your information anywhere. When your agent fetches records via `list_opportunities`, the deal values and company names pass through a stateless proxy. Vinkius retains zero data at rest.

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