Can my agent retrieve the AI summary of a specific Grain recording?

Yes. Use the 'get_insights' tool. The agent will fetch high-level abstract reductions including sentiment mapping, key discussion points, and summaries generated by Grain's ML engines natively.

How do I extract follow-up tasks from a meeting via chat?

Use the 'get_action_items' tool. Your agent will filter targeted follow-up tasks detected automatically by Grain within the meeting scope, enabling you to automate your post-call workflows flawlessly.

Can I search for meetings where a specific client was discussed through the agent?

Absolutely. Use the 'search_recordings' tool. Provide the keyword (e.g., client name). The agent will perform keyword scanning across all your meeting history and return ranked results natively.

Grain MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: Grain
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Grain as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="grain_agent",
    instruction=(
        "You help users interact with Grain "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Grain MCP Server

Connect your Grain.com account to any AI agent and take full control of your team meeting recordings, automated transcriptions, and AI-powered insights through natural conversation.

Google ADK natively supports Grain as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Meeting Orchestration — List all meeting recordings in your workspace and retrieve primary entry points for workspace interactions natively
Live Detail Retrieval — Resolve deep specific objects including transcripts and speaker attribution mapped by recording ID flawlessly
AI Transcription — Download full text structures with speaker attribution, parsing raw linguistic data to review critical discussions limitlessly
Contextual Insights — Extract high-level abstract reductions including sentiment mapping, summaries, and key takeaways generated by Grain's ML engines
Action Item Tracking — Filter targeted follow-up tasks detected automatically within meeting scopes to automate post-call workflows
Highlight Navigation — Identify curated clips and key moments generated by users within specific timestamps to focus on critical insights
Global Search — Execute keyword scanning across all meeting recordings to find specific discussions and ranked datasets synchronously
Asset Ingestion — Ingest remote video streams by passing public URLs for initial structural transformations and AI processing securely
Team Oversight — Retrieve fully enumerated team maps tracking workspace members and authenticated user profiles natively

The Grain MCP Server exposes 12 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Grain to Google ADK via MCP

Follow these steps to integrate the Grain MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from Grain via MCP

Why Use Google ADK with the Grain MCP Server

Google ADK provides unique advantages when paired with Grain through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Grain

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Grain tools with BigQuery, Vertex AI, and Cloud Functions

Grain + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Grain MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Grain and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Grain tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Grain regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Grain

Grain MCP Tools for Google ADK (12)

These 12 tools become available when you connect Grain to Google ADK via MCP:

get_action_items

Extract all action items identified from a recording

get_current_user

Retrieve the authenticated Grain user profile

get_insights

Retrieve AI-generated insights from a recording

get_recording

Retrieve full details of a specific meeting recording

get_transcript

Retrieve the full timestamped transcript of a meeting with speaker names

list_highlights

List all highlights (curated clips) from a recording

list_recordings

List all meeting recordings in the Grain workspace

list_shared_clips

List all clips that have been shared from the workspace

list_tags

List all tags used across recordings and highlights

list_workspace_members

List all members of the Grain workspace

search_recordings

Search across all meeting recordings by keyword

upload_video

Upload an external video URL for processing by Grain

Example Prompts for Grain in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Grain immediately.

"List my meeting recordings from today"

"What were the key decisions in the 'Roadmap Sync' meeting?"

"Search for recordings mentioning 'pricing strategy'"

Troubleshooting Grain MCP Server with Google ADK

Common issues when connecting Grain to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Grain + Google ADK FAQ

Common questions about integrating Grain MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.