Bring Key Value Store
to OpenAI Agents SDK

Connect your Upstash Redis serverless database securely to your conversational AI agent via their REST API. Activating this integration grants your AI the technical autonomy to function as a responsive database administrator, enabling it to scan live keys, read raw datastore strings, set temporal expiration values, and even debug in real-time straight from your chat or IDE terminal.

What you can do

• Read & Write Values — Fetch the exact string configuration of a stored key (get), or instruct the AI to inject a new value (set) complete with Time-To-Live (TTL) expiration limits.
• Data Structure Discovery — Perform pattern-based scans across your database to track down dynamically generated keys and inspect their underlying structures or lifespans (list_keys, get_key_info).
• Manage Counters — Safely increment or decrement numerical keys dynamically, perfect for managing rate limits, operational counters, or user session metrics directly during troubleshooting flows.
• Maintain Health — Ping the cluster instance for responsive status checks and remove (delete) specific keys or cache fragments completely.

How it works

1. Authorize the Upstash Redis MCP component in your active module extensions.
2. Obtain both the REST URL and REST Token connected to your intended database from your Upstash console and submit them in the configuration fields.
3. Chat natively with your AI to prompt a scan of cache items like 'session:*' or adjust active TTLs on a throttling profile.

Who is this for?

• Backend Developers — Verify cache hits, clear outdated session states intuitively, or seed temporary mock parameters rapidly without launching specialized desktop database clients like RedisInsight.
• DevOps Engineers — Inspect the rate-limiting structures or increment manual counter matrices safely during live-site debugging incidents.
• System Architects — Audit temporal key lifespans testing new eviction behaviors immediately as they write operational code logic.