How to Use the Upstash MCP in Google ADK

Q: How does the Google ADK handle large datasets from Upstash Redis?

The server supports reading all members of a set using smembers and fetching all fields/values in a hash with hgetall. These tools structure data for your long-context reasoning.

Q: Can I ensure multiple actions are atomic with Upstash Redis via the Google ADK?

The pipeline tool allows you to send commands together. While it groups them, if strict atomicity is non-negotiable, review the API for a multi-exec option.

Integrate Redis data operations into your enterprise workflows using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Upstash MCP to Google ADK

Create your Vinkius account to connect Upstash 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 Upstash with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check and manage key lifecycles

Use the `exists` tool to confirm a record's presence before acting on it. This prevents unnecessary API calls when you know the data isn't there. The `set` command lets you write new values, optionally setting an expiry time using the `ex` parameter. That guarantees your agents deal with timely and current information.

Increment counters and track metrics

If you need a simple running count, use `incr`. This tool initializes the key to 0 if it's missing, then returns the new value. It’s perfect for tracking usage or event counts. You can also decrement values with `decr`, which works just as reliably, ensuring your agents track resource consumption accurately.

Read and write complex sets

The `sadd` tool adds unique members to a Redis set. Duplicates are naturally ignored. This is perfect for collecting distinct IDs or tags. You can check membership quickly using `sismember`, which gives an instant, fast O(1) answer on whether a member exists.

Setup guide

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

The server supports reading all members of a set using `smembers` and fetching all fields/values in a hash with `hgetall`. These tools structure data for your long-context reasoning.

Absolutely. You can push values to either end of a list using `lpush` or `rpush`. The client then uses `lrange` to pull out specific ranges of elements.

The server manages strings, hashes, lists, and sets. This gives your agent flexibility—it can track everything from simple counters to complex grouping tags.

The `pipeline` tool allows you to send commands together. While it groups them, if strict atomicity is non-negotiable, review the API for a multi-exec option.

The server deals with structured data like strings and numeric values. It uses these core types to manage fields, members, and list entries across your enterprise applications.

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