How to Use the Splitwise MCP in Google ADK
Handle complex shared finances with Splitwise via Google ADK.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Splitwise MCP to Google ADK
Create your Vinkius account to connect Splitwise to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.
Key Capabilities
Expense Tracking for Shared Groups
To log a new cost, you call `create_expense` and pass the necessary details like total cost and individual user shares. This function makes sure every shared expense is recorded properly in your agent's workflow. If an entry needs to be removed from the ledger, use `delete_expense`. The MCP Server handles this cleanup process so your group finances stay accurate.
Listing and Inspecting Expenses
Want a full view of what's owed? Run `get_expenses` to get a comprehensive list. If you only need details on one item, `get_expense` pulls the specific record for you. You can also check group context using `get_group`, which gives the overall parameters of that particular set of shared debts.
Retrieving User and Friend Profiles
`get_user` lets your agent pull full profiles for any given user ID. You can also check who's in the group using `get_friends`, which lists all connected contacts. If you just need to verify details on one specific friend, `get_friend` provides those targeted records from the MCP Server.
Set up Splitwise MCP in Google ADK
Prerequisites
- Python 3.10+ installed
-
google-adkpackage (pip install google-adk) - Active Vinkius subscription with a valid endpoint token
- 1
Install Google ADK
Run
pip install google-adkto install the Agent Development Kit. MCP support is included via theMcpToolsetclass. - 2
Connect via SSE transport
Use
McpToolset.from_server()withSseServerParamspointing to your Vinkius endpoint. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Create an LlmAgent
Pass the returned
mcp_toolslist directly toLlmAgent(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 Splitwise tools in your ADK agent.
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="Splitwise_agent",
model="gemini-2.0-flash",
instruction="You have access to Splitwise tools via MCP.",
tools=mcp_tools,
) Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Splitwise. 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.
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 Splitwise MCP in Google ADK
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Splitwise MCP today
We host it, we monitor it, we maintain it. You just paste one token.