How to Use the Float MCP in Google ADK

Q: How do I initialize the Float toolset in Google ADK?

Instantiate the endpoint via McpToolset using your Vinkius HTTP URL. Pass this object directly into your LlmAgent tools array to let Gemini access listprojects and other endpoints.

Q: Can I write new project allocations with Float using Google ADK?

Yes, if you pass createallocation in your toolset parameters. The agent can analyze project needs and write new assignments directly back to your schedule.

Q: Can I filter which tools this MCP Server exposes to Gemini?

You use the toolnames filter parameter during initialization to limit exposure. For example, you can restrict an agent to only view listtimeoffs while hiding financial endpoints.

Connect Gemini models to Float via Google ADK to run resource forecasting alongside your enterprise BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Float MCP to Google ADK

Create your Vinkius account to connect Float 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 Float with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map departments to projects using Google ADK

`list_departments` feeds your Gemini agent the exact organizational structure of your agency. This allows the model to map specific teams to open client files without manual spreadsheet lookups. Because Google ADK handles long-context inputs, your agent can process every department listing from the MCP Server alongside massive project histories in a single prompt. It matches the right skills to the right jobs instantly.

Expose real-time project metrics to Gemini

`get_project` pulls live status updates directly into your enterprise data pipelines. Your Gemini agent reads these details to check if deadlines are slipping. You can join this data with your existing BigQuery tables using the ADK toolset. This gives your agent a complete view of budget usage and team capacity in one run.

Manage team availability with this MCP Server

`list_people` provides your agent with a complete roster of active employees and contract staff. This list serves as the foundation for all automated scheduling tasks. Running within Google's cloud infrastructure, the server uses secure HTTP transports. Your agent queries employee records to ensure project assignments match actual headcount.

Setup guide

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

Instantiate the endpoint via `McpToolset` using your Vinkius HTTP URL. Pass this object directly into your `LlmAgent` tools array to let Gemini access `list_projects` and other endpoints.

Yes, if you pass `create_allocation` in your toolset parameters. The agent can analyze project needs and write new assignments directly back to your schedule.

Gemini's structured execution loops let you build backoff logic in Python. This prevents your agent from hitting API limits when querying `list_allocations` across large teams.

You use the `tool_names` filter parameter during initialization to limit exposure. For example, you can restrict an agent to only view `list_time_offs` while hiding financial endpoints.

Names, department assignments, and time-off records are processed through zero-trust ephemeral environments. No personal records or allocation details are ever 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