How to Use the Mem0 MCP in Google ADK

Q: How does Mem0 integrate with the Google ADK toolset?

You wrap the MCP server in an McpToolset instance and pass it to your LlmAgent. The Google ADK agent then gains native access to all four memory management tools.

Connect Mem0 to your Google ADK pipelines to feed structured user memories directly into Gemini's long-context reasoning engine.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem0 MCP to Google ADK

Create your Vinkius account to connect Mem0 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 Mem0 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context grounding with Mem0 MCP Server

The `search_memories` tool allows your Google ADK agents to execute semantic searches over a user's entire history, returning highly relevant facts to feed Gemini's massive context window. This ensures the model reasons over actual user preferences rather than guessing. Instead of searching raw text files in BigQuery, the tool returns structured, ranked memories. Your agent can immediately ground its responses in verified historical facts, reducing hallucinations during long reasoning steps.

Real-time context writing from Vertex AI

The `add_memory` tool extracts key details from user inputs and saves them to Mem0 directly from your Google ADK agent loop. As Gemini processes a conversation, it identifies preferences and writes them as persistent facts. This MCP-backed persistent storage operates outside of Google Cloud's temporary session state. Even if the user closes their browser, their preferences remain stored and ready for the next session.

Profile auditing for enterprise Google ADK agents

The `get_memories` tool lists every recorded fact for a specific user ID, giving your Google ADK agent a complete picture of the user's profile. You can use this tool to display stored preferences back to the user for validation. If the user decides a stored fact is outdated, the agent can call `delete_memory` to remove that specific entry. This keeps the memory database accurate and aligned with your enterprise data governance policies.

Setup guide

Set up Mem0 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 Mem0 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="Mem0_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mem0 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 Mem0. 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 Mem0 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 Mem0 MCP in Google ADK

You wrap the MCP server in an `McpToolset` instance and pass it to your `LlmAgent`. The Google ADK agent then gains native access to all four memory management tools.

Yes, Gemini's native tool-calling capabilities allow it to decide when to run these MCP tools based on the user's conversational intent.

No, it complements it. While BigQuery handles analytical data, Mem0 provides low-latency semantic recall of user facts during live agent conversations.

The tool uses semantic vector search to rank memories by relevance. It returns only the top matches, preventing your agent from getting overwhelmed by irrelevant historical data.

Yes, all user preferences and facts are transmitted over secure TLS connections and stored in zero-trust, ephemeral sandboxes. This prevents unauthorized access to sensitive user data within your Google Cloud ecosystem.

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