How to Use the Granola MCP in Google ADK

Q: Can Google ADK analyze multiple Granola documents at once?

Yes, you can use getdocumentsbatch to fetch multiple meeting records in a single call. This is highly efficient when taking advantage of Gemini's large context window.

Q: How do I list only the meetings that happened last week?

Use the listbydate MCP tool to query a specific date range. This filters out irrelevant meetings and keeps your agent's context window clean.

Feed long-context Gemini models with meeting data using Google ADK and Granola.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Granola MCP to Google ADK

Create your Vinkius account to connect Granola 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 Granola with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed 1M-token Gemini models via Google ADK

The `get_transcript` tool extracts complete, speaker-labeled meeting records directly into your Gemini long-context window. Because Google ADK supports massive token limits, your agent can ingest hours of raw conversation to find subtle technical requirements. Combining this transcript data with your existing BigQuery tables lets you cross-reference meeting commitments against actual project deliverables. Your agent runs these complex analytical workflows without running out of memory.

Run enterprise-grade search across your MCP Server

The `search_documents` tool executes full-text search queries across your entire meeting database. Your Google ADK agent uses this tool to locate specific decisions before writing updates back to your Vertex AI pipelines. To keep your agent focused, you can use the tool_names filter in the ADK setup to expose only this search capability. This prevents the model from wasting compute on tools like `list_folders` when it only needs to find specific text.

Map meeting participants to cloud infrastructure

The `get_participants` tool retrieves the list of people present in any recorded meeting. Your agent uses this identity data to map action items to specific team members in your cloud directory. By chaining this with `get_action_items`, you automate the assignment of tasks based on who was actually in the room. The entire process runs through secure HTTP transport endpoints managed by Vinkius.

Setup guide

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

You instantiate McpToolset with your Vinkius HTTP endpoint URL and pass it to your LlmAgent. This exposes the Granola tools directly to your Gemini models.

Yes, you can use get_documents_batch to fetch multiple meeting records in a single call. This is highly efficient when taking advantage of Gemini's large context window.

Yes, the ADK supports both transport layers for this MCP Server. For production deployments, we recommend the managed HTTP endpoint provided by Vinkius to ensure reliable uptime.

Use the list_by_date MCP tool to query a specific date range. This filters out irrelevant meetings and keeps your agent's context window clean.

Your meeting summaries and transcripts flow through TLS 1.3 encrypted tunnels directly to your Google Cloud environment. No MCP data is stored on intermediate servers during the transit.

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