How to Use the Housecall Pro MCP in Google ADK

Q: How do I initialize the Housecall Pro MCP integration with Google ADK?

Run pip install google-adk. Create a StreamableHttpServerParameters object with your URL. Wrap that in an McpToolset and pass it to your LlmAgent initialization.

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

Yes. You provide an array of strings to the toolnames parameter. This restricts the agent to specific functions like getcustomer while hiding administrative tools like listwebhooks.

Q: How does the Housecall Pro MCP Server handle Gemini's long context?

The server returns raw JSON from endpoints like listjobs. Gemini ingests the entire payload into its 1M+ token window, allowing it to reason across months of dispatch data simultaneously.

Connect Gemini agents to the Housecall Pro MCP Server using Google ADK for enterprise field service operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Housecall Pro MCP to Google ADK

Create your Vinkius account to connect Housecall Pro 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 Housecall Pro with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed job histories into Gemini

Pulling hundreds of past work orders using `list_jobs` feeds directly into Gemini's massive context window. The model retains the entire service history for a neighborhood or commercial client. You no longer have to chunk or summarize old dispatch records. Binding the MCP Server to your agent requires the `McpToolset` class. The agent cross-references active jobs with `list_technicians` to map out seasonal demand patterns without losing the thread.

Cross-reference invoices with BigQuery

Grabbing the latest field service billing data with `list_invoices` lets you cross-reference records against BigQuery. Enterprise teams already have their financial data in Google Cloud. Your agent pulls the operational data and matches it against the warehouse. You track discrepancies instantly. If a technician quotes a job using `list_estimates`, the agent checks historical material costs in Vertex AI before approving the margin.

Map out customer service networks

Hitting `get_company` pulls the core business profile for commercial account management. The agent iterates through `list_customers` to map out every franchise location associated with the main account. Google ADK lets you pass a `tool_names` filter to the toolset. If you only want the agent reading price books, you expose `list_price_list_items` and block the rest of the endpoints.

Setup guide

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

Run `pip install google-adk`. Create a `StreamableHttpServerParameters` object with your URL. Wrap that in an `McpToolset` and pass it to your `LlmAgent` initialization.

Yes. You provide an array of strings to the `tool_names` parameter. This restricts the agent to specific functions like `get_customer` while hiding administrative tools like `list_webhooks`.

The server returns raw JSON from endpoints like `list_jobs`. Gemini ingests the entire payload into its 1M+ token window, allowing it to reason across months of dispatch data simultaneously.

Google ADK supports both Stdio and HTTP transports. For remote execution on Vinkius, you configure the HTTP transport to communicate with your isolated endpoint.

The tools read direct invoice amounts and residential gate codes. We enforce a zero-trust architecture where the server requires a unique endpoint token for every session. No traffic routes through public internet nodes without strict authentication.

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