How to Use the Circle.so MCP in Google ADK

Q: How do I configure Circle.so within my Google ADK setup?

You initialize the McpToolset using the Vinkius MCP Server HTTP URL and pass it to your LlmAgent. This exposes the Circle.so tools directly to Gemini models running on Google Cloud.

Q: Can my Google ADK agent write Circle.so data to BigQuery?

Yes, your agent can. It uses tools like listcommunitymembers to fetch active users and writes that structured data directly into your BigQuery tables.

Build Gemini-powered Google ADK agents that analyze your Circle.so community data inside your Google Cloud ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Circle.so MCP to Google ADK

Create your Vinkius account to connect Circle.so 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 Circle.so with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process Circle.so topics with Google ADK

The `list_community_topics` tool feeds discussion threads directly into your Gemini model's 1M-token context window. This allows your agent to analyze months of community discussions in a single run. You can export these parsed discussion topics directly into BigQuery from your Google ADK environment. Running SQL queries over your community's most active discussions becomes simple with this setup.

Track event engagement using this MCP Server

Using `list_community_events` and `list_community_members`, your Gemini agent tracks which members are showing up to community meetups. The agent pulls raw event lists and correlates them with member profiles. This MCP Server integration allows you to run predictive models on Vertex AI to see which events drive the highest long-term retention. You get direct access to community metrics without manual exports.

Inspect admin actions and post comments

The `get_my_circle_profile` and `list_post_comments` tools let your Google ADK agent verify admin configurations and audit comment sections. Your agent reads the admin metadata to ensure proper access controls. By filtering tools in your McpToolset, you can restrict your Gemini agent to only read comments, keeping sensitive admin profiles locked down. This keeps your Google Cloud agent secure and compliant.

Setup guide

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

You initialize the `McpToolset` using the Vinkius MCP Server HTTP URL and pass it to your `LlmAgent`. This exposes the Circle.so tools directly to Gemini models running on Google Cloud.

Yes, your agent can. It uses tools like `list_community_members` to fetch active users and writes that structured data directly into your BigQuery tables.

Yes, it does. The ADK auto-discovers all 8 tools, including `list_community_spaces` and `list_space_groups`, so your agent can navigate your entire community layout.

You can restrict access by passing a specific list of tool names to your `McpToolset` constructor. This prevents the agent from calling administrative tools like `get_my_circle_profile`.

Yes, absolutely. This MCP Server processes your post text retrieved via `list_community_posts` inside secure, ephemeral V8 isolates. No community content is cached or stored on Vinkius disks.

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