How to Use the Upstash MCP in Pydantic AI

Q: Can I list and manage keys using Upstash Redis within Pydantic AI?

Yes. The listkeys tool lets you find keys by prefix or suffix matching. Just watch out: listing large key spaces can slow down the database, so use it sparingly.

Q: What is the recommended way to handle multiple Upstash Redis commands with Pydantic AI?

Use the pipeline tool. It sends a batch of commands as a structured array. This allows your agent to execute several actions in one go, while maintaining clear data flow for validation.

Q: How does Upstash Redis handle TTL expiration when using Pydantic AI?

You can set an expiry time with expire on any key. When the Time-To-Live hits zero, the data automatically deletes itself, keeping your records clean and up-to-date.

Type-safe Redis operations for guaranteed correctness with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Upstash to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify and retrieve string data

Your agent uses the `get` tool to fetch a value from Upstash Redis. Because of Pydantic's validation, if the key is missing, you get an explicit null response. The primary write operation remains simple: using `set` guarantees that the data written is what your system expects.

Manage complex hash records

The `hgetall` tool pulls every field and value from a Redis hash into an object. Pydantic validates this structure, so you never get unexpected fields. Similarly, use `hset` to reliably update specific fields in existing hashes or create new ones.

Track metrics with reliable counters

The `incr` tool handles numeric increases. It initializes the key to 0 if it doesn't exist, so you can count right away without worrying about setup. For tracking decreases, `decr` returns the new value after decrementing, keeping your resource counts accurate.

Setup guide

Set up Upstash MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "upstash-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Upstash tools.",
)

result = await agent.run("List recent Upstash transactions")
print(result.output)

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 Pydantic AI

Pydantic validates every response against defined schemas. If the API returns unexpected data—say, a missing field in an object—the agent fails loudly with a validation error, preventing silent corruption.

Yes. The `list_keys` tool lets you find keys by prefix or suffix matching. Just watch out: listing large key spaces can slow down the database, so use it sparingly.

Use the `pipeline` tool. It sends a batch of commands as a structured array. This allows your agent to execute several actions in one go, while maintaining clear data flow for validation.

The server deals with strings, hashes, lists, and sets. These core structures ensure that the data your agent reads or writes always conforms to a predictable type.

You can set an expiry time with `expire` on any key. When the Time-To-Live hits zero, the data automatically deletes itself, keeping your records clean and up-to-date.

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