How to Use the HiFlow MCP in Google ADK

Q: How do I initialize HiFlow with Google ADK?

Install google-adk and create a McpToolset. Pass your endpoint URL via StreamableHttpServerParameters. Assign this toolset to your LlmAgent under the tools parameter.

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

Yes. Use the toolnames parameter when defining your toolset. This allows you to expose getinvoice while hiding createcustomer from the model.

Q: Will HiFlow work with Gemini's long context in Google ADK?

Yes. You can run listcustomers to pull your entire CRM database. Gemini's massive token window easily absorbs the full JSON response for cross-referencing.

Connect HiFlow to Google ADK to let Gemini agents manage your jobs and invoices.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HiFlow MCP to Google ADK

Create your Vinkius account to connect HiFlow 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 HiFlow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed HiFlow data into Google ADK

Gemini models thrive on massive context windows. You can dump thousands of records from `list_invoices` and `list_estimates` straight into the prompt. That model digests the entire financial history without breaking a sweat. This changes how you approach reporting. Instead of building complex SQL joins, your agent simply calls `list_jobs` and cross-references the output with your existing BigQuery tables. Everything happens naturally within the reasoning loop.

Automate customer workflows

Enterprise agents need to act on information, not just read it. Exposing the `create_customer` tool lets your Gemini agent onboard new clients automatically based on Vertex AI triggers. That process requires zero manual data entry. Existing accounts are just as easy to handle. When a support ticket comes in, the agent fires `get_customer` to grab the exact profile. It then checks `get_activity` to see what happened on the account recently.

Analyze timesheets with the MCP Server

Tracking billable hours usually requires jumping between tabs. Your Google agent can run `list_timesheets` to pull every logged hour across the company. It maps those hours against active projects using `get_job`. Setup takes minutes. You initialize a `McpToolset` with your HTTP parameters and pass it to your `LlmAgent`. If you only want the agent to see specific endpoints, use the `tool_names` filter to restrict access to `get_me` or other safe read-only tools.

Setup guide

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

Install `google-adk` and create a `McpToolset`. Pass your endpoint URL via `StreamableHttpServerParameters`. Assign this toolset to your `LlmAgent` under the `tools` parameter.

Yes. Use the `tool_names` parameter when defining your toolset. This allows you to expose `get_invoice` while hiding `create_customer` from the model.

Yes. You can run `list_customers` to pull your entire CRM database. Gemini's massive token window easily absorbs the full JSON response for cross-referencing.

The framework supports both Stdio and HTTP transports natively. Configure your server parameters to point to your provided endpoint and include the necessary authentication headers.

All financial records and job details pass through a zero-trust architecture. The managed MCP infrastructure never caches your `get_estimate` payloads. Authentication relies on a single endpoint token that authenticates the strict boundary between your cloud environment and the API.

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