How to Use the Grain MCP in Google ADK

Q: How does Google ADK authenticate with the Grain MCP server?

You configure the McpToolset with your Vinkius HTTP endpoint. Vinkius handles the underlying MCP connection, so your Gemini-powered agent can immediately call listworkspacemembers without managing API keys manually.

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

Yes, you can pass a toolnames filter to your McpToolset initialization. This ensures your agent only exposes specific MCP tools like getinsights while hiding administrative ones like listworkspacemembers.

Q: Can my agent upload external video files to Grain?

Yes, using the uploadvideo tool. Your agent can take a video URL from a Google Cloud Storage bucket, send it to Grain for processing, and then retrieve the transcript once complete.

Feed Grain transcripts and meeting insights directly to your Google ADK agents with enterprise-grade security.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grain MCP to Google ADK

Create your Vinkius account to connect Grain 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 Grain with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze long-form meetings with Google ADK

Gemini models excel at processing massive contexts, making them perfect for digesting entire meeting catalogs. By connecting this MCP server, your Google ADK agent can call `get_transcript` to load full, timestamped discussions directly into its reasoning loop. This lets you query hours of conversations without hitting token limits. Your agent can cross-reference multiple calls by running `list_recordings` and building a timeline of project updates.

Sync meeting action items to BigQuery

Export what was promised in a meeting directly to your data warehouse. Your Google ADK agent can run `get_action_items` on a recording and format the output to match your structured BigQuery tables. This bridges the gap between unstructured voice calls and your enterprise analytics. You don't need to write custom parsers; the agent handles the extraction and database insert in one flow.

Search workspace records via Gemini

Let your team query their meeting history using natural language. The agent uses `search_recordings` to find matches across your entire workspace, then pulls specific details using `get_recording`. This replaces basic keyword search with intelligent retrieval. The agent can find the exact moment a specific feature was debated, pull the speaker names, and summarize the final decision.

Setup guide

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

You configure the `McpToolset` with your Vinkius HTTP endpoint. Vinkius handles the underlying MCP connection, so your Gemini-powered agent can immediately call `list_workspace_members` without managing API keys manually.

Yes, you can pass a `tool_names` filter to your `McpToolset` initialization. This ensures your agent only exposes specific MCP tools like `get_insights` while hiding administrative ones like `list_workspace_members`.

Because Gemini handles huge token counts, your Google ADK agent can ingest entire transcripts retrieved via `get_transcript` instead of relying on short summaries. This preserves the original tone and exact phrasing of your meetings.

Yes, using the `upload_video` tool. Your agent can take a video URL from a Google Cloud Storage bucket, send it to Grain for processing, and then retrieve the transcript once complete.

Absolutely. All meeting video files, transcripts, and notes are processed through ephemeral V8 sandboxes. No data is stored on our servers, ensuring your sensitive corporate conversations remain completely private.

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