How to Use the Mem AI (Knowledge Workspace) MCP in Google ADK

Q: How do I register the Mem AI (Knowledge Workspace) tools in Google ADK?

Instantiate McpToolset with your Vinkius HTTP URL, then pass it to your LlmAgent tools array. The Gemini model automatically discovers all twelve endpoints and knows when to call them.

Q: Can I restrict which Mem AI (Knowledge Workspace) tools a Google ADK agent can access?

Yes, configure the optional toolnames filter when initializing your toolset. This MCP toolset configuration lets you expose read-only tools like searchmems while blocking destructive ones like deletemem entirely.

Q: What happens if my agent needs to quickly capture a thought?

The agent can execute memit to generate a rapid, automated text block. This MCP tool is perfect for logging quick status updates directly from a terminal or automated pipeline.

Connect your Google ADK agents to Mem AI to search, update, and organize your knowledge base using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem AI (Knowledge Workspace) MCP to Google ADK

Create your Vinkius account to connect Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed entire collections to Gemini models

Gemini's million-token window shines when you feed it deep context from your Mem AI workspace. By using `list_collection_mems`, your Google ADK agent can pull every single note from a specific folder and analyze them all at once. You don't have to worry about running out of token space when querying large datasets. This MCP Server lets your Google ADK agent inspect metadata using `get_collection` to decide exactly which documents to ingest.

Sync Google Cloud data to Mem AI

If you have enterprise data sitting in BigQuery, your Google ADK agent can process those records and write them directly to your Mem AI workspace. The agent uses `create_mem` to convert raw SQL rows into clean markdown notes inside the workspace. This bridges the gap between structured BigQuery databases and your team's collaborative Mem workspace. Your Google ADK agent can keep both systems in sync automatically by running `update_mem` whenever data changes.

Semantic Search across Google ADK

Instead of hardcoded keyword matching, your Google ADK agent uses `search_mems` to find notes based on conceptual meaning. This allows Gemini to connect the dots between vague user queries and highly technical Mem documentation. Once the agent locates the right files, it can group them dynamically. It calls `create_collection` to build custom thematic groupings on the fly based on the Mem search results.

Setup guide

Set up Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) 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="Mem AI (Knowledge Workspace)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mem AI (Knowledge Workspace) 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 Mem.ai. 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 Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) MCP in Google ADK

Instantiate `McpToolset` with your Vinkius HTTP URL, then pass it to your `LlmAgent` tools array. The Gemini model automatically discovers all twelve endpoints and knows when to call them.

Yes, configure the optional `tool_names` filter when initializing your toolset. This MCP toolset configuration lets you expose read-only tools like `search_mems` while blocking destructive ones like `delete_mem` entirely.

Gemini's long-context window easily handles the heavy payloads returned by `list_mems`. However, to optimize latency, you should still guide your agent to use `search_mems` for targeted queries.

The agent can execute `mem_it` to generate a rapid, automated text block. This MCP tool is perfect for logging quick status updates directly from a terminal or automated pipeline.

Your enterprise data stays safe because Vinkius executes all tool calls in a secure, zero-trust V8 sandbox. Your knowledge vectors and personal notes are never written to disk or exposed to external networks.

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