How to Use the Fellow MCP in Google ADK

Q: How do I register Fellow tools in my Google ADK agent?

You initialize the McpToolset using the Streamable HTTP server parameters pointing to your Vinkius endpoint. Pass this toolset directly to your LlmAgent constructor to expose tools like listmeetings to Gemini.

Q: Can I restrict which Fellow tools my Google ADK agent can access?

Yes, use the optional toolnames filter in the toolset configuration to restrict access. For example, you can expose listactionitems while blocking write tools like completeactionitem.

Feed your Gemini models live meeting data and track action items directly within your Google ADK enterprise pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to Google ADK

Create your Vinkius account to connect Fellow 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 Fellow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Meeting Streams inside the Google ADK

Retrieving meeting series data with `list_streams` and `get_stream` gives your Google ADK agent access to recurring meeting structures. This MCP tool allows Gemini models with 1M+ token contexts to analyze months of team updates in a single run. Merging this structural data with BigQuery records lets your enterprise pipeline track project health over time. You get a direct line from meeting cadences to actual developer output.

Update Workspace Tasks with Gemini Reasoning

Writing task updates using `create_action_item` and `complete_action_item` allows your Google ADK agent to modify workspace states based on model decisions. This MCP connection translates natural language commands into structured API updates. Using `list_action_items` lets the pipeline pull pending tasks directly into your Gemini reasoning loop. The model checks what is outstanding before drafting project status reports.

Extract Context from Notes and Meetings

Exposing raw meeting content through `list_notes` and `get_note` provides the exact text your Google ADK agents need to build status summaries. The agent reads the text, identifies key decisions, and saves the output back to your cloud storage. Calling `get_meeting` pulls the specific metadata for any sync, including the list of attendees. This ensures your automated summaries accurately attribute decisions to the correct participants.

Setup guide

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

You initialize the `McpToolset` using the Streamable HTTP server parameters pointing to your Vinkius endpoint. Pass this toolset directly to your `LlmAgent` constructor to expose tools like `list_meetings` to Gemini.

Yes, use the optional `tool_names` filter in the toolset configuration to restrict access. For example, you can expose `list_action_items` while blocking write tools like `complete_action_item`.

Yes, the framework connects to this MCP Server over streamable HTTP for cloud deployments or Stdio for local testing. Vinkius manages the authentication layer, giving your agent a single secure endpoint to query.

Absolutely, you can use Gemini's reasoning to join notes retrieved via `get_note` with structured metrics in BigQuery. This allows the agent to verify if decisions made in meetings correlate with system performance.

Your action items and meeting details are processed in memory within secure, ephemeral V8 isolates. The integration uses a single-token auth model, meaning your master API credentials are never exposed to the LLM or stored on Vinkius.

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