How to Use the Attio MCP in Google ADK

Q: Attio Google ADK initialization

Pass your Vinkius URL into StreamableHttpServerParameters and wrap it in an McpToolset. Then hand that toolset to your LlmAgent under the tools argument.

Q: Filter Attio tools Google ADK

Yes. Use the toolnames filter in your toolset configuration to expose only specific endpoints like queryrecords or getobject.

Q: Diagnose connection errors

The agent can run getaccountcheck to diagnose the issue. It verifies whether the token is valid and the workspace is accessible.

Give your Google ADK agents read and write access to the Attio MCP Server. Feed massive CRM datasets directly into Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Attio MCP to Google ADK

Create your Vinkius account to connect Attio 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 Attio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK context expansion via MCP

Gemini models handle massive context windows. When you connect this server, your agent can pull hundreds of CRM entries using `query_records` and load them straight into memory. It cross-references deals against your BigQuery tables natively. Finding specific needles in that haystack is straightforward. The agent runs `search_records` to execute a global fuzzy search across your entire workspace. It grabs the relevant IDs and pulls the full metadata using `get_record`.

Enterprise-grade writes

Agents running on Google Cloud need reliable ways to modify external state. Pushing a new lead from Vertex AI into your CRM happens through the `create_record` tool. The payload goes through the Vinkius endpoint and updates your workspace instantly. Handling duplicates requires a different approach. Your agent calls `assert_record` to upsert data safely. If the company exists, it updates the fields; if not, it creates a brand new entry.

Schema discovery on the fly

Hardcoding CRM schemas creates brittle agents. Your Google ADK setup can inspect the workspace dynamically by calling `list_objects`. It figures out exactly what tables exist before trying to interact with them. Column definitions are just as accessible. The agent fires off `list_attributes` to see what fields are available on a specific object. You can filter which of these tools the agent sees using the `tool_names` parameter in your `McpToolset` config.

Setup guide

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

Pass your Vinkius URL into `StreamableHttpServerParameters` and wrap it in an `McpToolset`. Then hand that toolset to your `LlmAgent` under the `tools` argument.

Yes. Use the `tool_names` filter in your toolset configuration to expose only specific endpoints like `query_records` or `get_object`.

The framework supports both Stdio and HTTP transports natively. Since Vinkius provides a managed MCP endpoint, you will use the HTTP transport option.

The agent can run `get_account_check` to diagnose the issue. It verifies whether the token is valid and the workspace is accessible.

Vinkius processes your contact names, phone numbers, and company profiles in a zero-trust environment. The execution environment is completely isolated and tears itself down the millisecond the API returns a response.

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