How to Use the FynCom MCP in Google ADK

Q: How do I connect FynCom to a Google ADK agent?

Instantiate an McpToolset with the FynCom MCP server URL and pass it into your LlmAgent's tools list. The ADK handles the tool discovery, making functions like sendreward immediately available.

Q: How do I manage my FynCom reward budget with a Google ADK agent?

Have your agent call getwalletbalance on a schedule. You can program it to send a notification through Google Cloud services or pause campaigns if the balance drops below a set threshold.

Q: Can I limit which FynCom tools my Google ADK agent can use?

Yes. The McpToolset constructor in the Google ADK has a toolnames filter. Use it to create toolsets that only expose specific FynCom functions, like addrewardlead, to certain agents.

Connect your Google ADK agent to FynCom and trigger micro-rewards based on your enterprise data in BigQuery and Vertex AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FynCom MCP to Google ADK

Create your Vinkius account to connect FynCom 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 FynCom with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Rewards from Google Cloud

Here's the thing: your data's in BigQuery, but your users are somewhere else. This server bridges that gap. A Gemini-powered agent in Google ADK can analyze your cloud data, spot a key user action, and then immediately call FynCom's `send_reward` tool. This connects your massive datasets directly to customer engagement. The agent has the context from your Google Cloud data to know exactly when a reward will have the most impact. It’s not guessing; it’s acting on your business intelligence.

Manage Budgets with Your Agent

An enterprise agent has to be accountable. Program your agent to use `get_wallet_balance` to monitor funds in real time. It can use `list_reward_campaigns` to understand budget allocation across different marketing efforts. Better yet, have the agent pull data using `list_reward_history` and join it with your own finance tables in BigQuery to generate custom spending reports. This closes the loop between marketing actions and financial oversight.

Filter Tools for Focused Agents

You don't want every agent to have the keys to the kingdom. Google ADK lets you filter the tools exposed to each agent. You can build a specialized 'finance' agent that only gets access to `get_wallet_balance` and `list_reward_history`. Meanwhile, your 'marketing' agent can have `add_reward_lead` and `get_campaign_details` but not the ability to send money. This is how you build secure, role-based agent systems on Google Cloud, all communicating through a single MCP server endpoint.

Setup guide

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

Instantiate an `McpToolset` with the FynCom MCP server URL and pass it into your `LlmAgent`'s tools list. The ADK handles the tool discovery, making functions like `send_reward` immediately available.

Yes, that's exactly what it's for. Your agent can run a query on BigQuery, identify users who meet your criteria, and then directly call the `send_reward` tool for each one.

Have your agent call `get_wallet_balance` on a schedule. You can program it to send a notification through Google Cloud services or pause campaigns if the balance drops below a set threshold.

Yes. The `McpToolset` constructor in the Google ADK has a `tool_names` filter. Use it to create toolsets that only expose specific FynCom functions, like `add_reward_lead`, to certain agents.

The FynCom server only ever sees reward-specific data like lead emails or campaign IDs. It has no access to your data in BigQuery or the agent's reasoning process in Vertex AI. Each transaction is isolated.

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