How to Use the AgentFire MCP in Google ADK

Q: How do I configure AgentFire within Google ADK?

Install google-adk via pip. Initialize a McpToolset with the Vinkius endpoint URL and pass it to your LlmAgent under the tools parameter.

Q: Can my Google ADK agent search AgentFire listings automatically?

Yes. The agent decides when to call the searchlistings tool based on the user's prompt. It parses the returned JSON and formats the properties into a readable response.

Q: How do I filter which AgentFire tools the Google ADK agent can use?

You pass a specific list of strings to the toolnames parameter when setting up the toolset. This prevents the agent from accessing functions like updatelead if you want a read-only setup.

Q: Does the AgentFire MCP Server support HTTP transport in Google ADK?

The system works perfectly with the StreamableHttpServerParameters class. You provide the Vinkius URL and your authentication token to establish the connection.

Bring AgentFire property listings and client contacts into Google ADK to build enterprise real estate agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentFire MCP to Google ADK

Create your Vinkius account to connect AgentFire 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 AgentFire with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search real estate inventory

AgentFire exposes your active property database to Google's agent framework via this MCP server. An agent runs `search_listings` to find homes matching specific criteria, then uses `get_listing` to pull the exact dimensions, pricing, and status. Because Gemini models handle massive context windows, you can dump hundreds of listings into the prompt at once for complex market analysis. Enterprise agents need reliable access to inventory data. By calling `list_listings`, your system syncs the entire available catalog to BigQuery for long-term storage. This setup lets your agent cross-reference live market data against historical sales records sitting in your Google Cloud infrastructure.

Capture buyers with the AgentFire MCP Server

Managing your real estate pipeline requires creating new records the moment a buyer shows interest. Your agent triggers `create_lead` to log the prospect, requiring just an email address to start. As the conversation progresses, the system fires off `update_lead` to add phone numbers, budgets, or preferred neighborhoods without overwriting existing fields. Pulling historical context on a buyer is just as crucial. The `get_lead` tool fetches a specific person's file, while `list_leads` grabs the entire pipeline. You restrict which of these tools the agent sees by using the `tool_names` filter in your setup, keeping the agent focused strictly on data entry if needed.

Sync contacts to Google Cloud

Connecting your brokerage identity to your automated systems starts with checking your profile. The `get_profile` tool pulls your specific agent details so the Gemini model knows exactly who it represents. You also run `check_agentfire_status` to ensure the API is responding before kicking off large data syncs. Brokerages live and die by their network. Using `list_contacts`, your agent pulls your entire rolodex into memory. You then pipe that output directly into Vertex AI to run predictive models on which clients are most likely to buy or sell this quarter.

Setup guide

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

Install `google-adk` via pip. Initialize a `McpToolset` with the Vinkius endpoint URL and pass it to your `LlmAgent` under the tools parameter.

Yes. The agent decides when to call the `search_listings` tool based on the user's prompt. It parses the returned JSON and formats the properties into a readable response.

You pass a specific list of strings to the `tool_names` parameter when setting up the toolset. This prevents the agent from accessing functions like `update_lead` if you want a read-only setup.

The system works perfectly with the `StreamableHttpServerParameters` class. You provide the Vinkius URL and your authentication token to establish the connection.

Vinkius processes your real estate leads and contact lists through a zero-trust architecture. The MCP connection is stateless, meaning your client phone numbers and budgets never touch a hard drive during the transaction.

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