How to Use the folk MCP in Google ADK

Q: How do I restrict which folk tools my Google ADK agent can use?

The McpToolset in the Google ADK has a toolnames filter. You can provide a list of allowed tool names, for instance, only allowing listcontacts and listgroups for a reporting agent.

Q: Can an agent use this to sync folk contacts into a BigQuery table?

Yes, that's a primary use case. The agent would call listcontacts, then iterate through the list, calling getcontactdetails for each one and writing the structured data to a BigQuery table.

Q: Can I build an agent with the Google ADK to summarize my team's interactions from folk?

Definitely. Use listcontacts to get your team's key accounts, then listinteractions for each one. Feed that entire transcript into a Gemini model to get a high-level summary of the week's activity.

Connect your folk contacts to Google Cloud and let Gemini-powered agents act on them with the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect folk MCP to Google ADK

Create your Vinkius account to connect folk 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 folk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bridge CRM and BigQuery

Your contact data in folk is valuable, but it's even better when combined with your enterprise data. Use `list_contacts` to pull your entire CRM database. Then, have your Google ADK agent cross-reference it with customer data in BigQuery. This turns your agent into a powerful research tool. It can identify high-value leads in folk that aren't in your product database yet, or find churn risks by comparing `list_interactions` against usage logs.

Long-Context Relationship Analysis

Gemini's huge context window changes the game. Your agent can pull years of history for a key account using `list_interactions` and `list_contact_notes`. It can hold all that context in memory to generate a truly insightful summary. You're not just getting a list of events; you're getting a narrative. This is perfect for generating executive briefings or onboarding a new account manager. The agent can see the whole story, not just the last few emails.

Your folk MCP Server on Google Cloud

The Google ADK is built for the Google Cloud ecosystem. This folk MCP server slots right in. Your agent can `create_contact` in folk based on a trigger from a Pub/Sub topic or a new row in a Google Sheet. You're not just automating tasks, you're building data pipelines that react to events across your entire cloud infrastructure. The agent becomes the smart glue between your CRM and the rest of your business.

Setup guide

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

The `McpToolset` in the Google ADK has a `tool_names` filter. You can provide a list of allowed tool names, for instance, only allowing `list_contacts` and `list_groups` for a reporting agent.

Yes, that's a primary use case. The agent would call `list_contacts`, then iterate through the list, calling `get_contact_details` for each one and writing the structured data to a BigQuery table.

A solid first step is an agent that monitors a 'New Leads' group in folk. It can use `list_contacts` to find them, `get_contact_details` to enrich their profile with other data, and then `create_contact` to add them to a different, more qualified group.

Definitely. Use `list_contacts` to get your team's key accounts, then `list_interactions` for each one. Feed that entire transcript into a Gemini model to get a high-level summary of the week's activity.

This MCP server acts as a pass-through. Your contact records, notes, and interaction logs are never persisted on our systems. Each request is handled in a temporary, sandboxed V8 Isolate on Vinkius, and all connections are encrypted end-to-end.

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