
Connect Upstash to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run database commands without ever opening a terminal.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 23 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 23 available through Upstash.
- 01
Del
Deletes a specific key from your Upstash Redis instance. This action is permanent and cannot be undone.
- 02
Expire
Sets a time to live (TTL) on a key so it deletes itself automatically after the timeout.
- 03
Get
Retrieves the string value associated with a specific key.
- 04
Hget
Fetches a specific field value from a Redis hash.
05-08
4 capabilities in this set.
Part of 23 available through Upstash.
- 05
Hset
Sets a field in a Redis hash, creating the hash if it doesn't exist yet.
- 06
List keys
Finds keys in your database using pattern matching like prefixes or suffixes.
- 07
Llen
Returns the total number of elements currently in a Redis list.
- 08
Lrange
Gets a specific range of elements from a Redis list using start and stop indices.
09-12
4 capabilities in this set.
Part of 23 available through Upstash.
- 09
Pipeline
Sends a batch of multiple commands in a single request to reduce overhead.
- 10
Publish
Sends a message to a specific channel for subscribers to receive.
- 11
Rpush
Adds new values to the right side of a Redis list.
- 12
Sismember
Checks if a specific member exists within a Redis set.
13-16
4 capabilities in this set.
Part of 23 available through Upstash.
- 13
Smembers
Returns every unique member stored in a Redis set.
- 14
Srem
Removes specified members from a Redis set.
- 15
Ttl
Checks how much time remains before a key expires.
- 16
Decr
Reduces a numeric value in your database by one.
17-20
4 capabilities in this set.
Part of 23 available through Upstash.
- 17
Exists
Checks if a key is present in the database without pulling its data.
- 18
Hgetall
Retrieves every field and value stored within a Redis hash.
- 19
Incr
Increases a numeric value in your database by one.
- 20
Key type
Identifies the data type of a specific key.
21-23
3 capabilities in this set.
Part of 23 available through Upstash.
- 21
Lpush
Adds new values to the left side of a Redis list.
- 22
Sadd
Adds new, unique members to a Redis set.
- 23
Set
Writes a string value to a key and can optionally set an expiration time.
Real work
What teams actually run
Feature Flag Management
Quickly toggle application features by updating string keys with specific TTLs.
Session Debugging
Inspect user session data stored in hashes to troubleshoot login issues.
Rate Limit Auditing
Check and adjust numeric counters used for request throttling.
Queue Inspection
View and manage elements in Redis lists used for background task processing.
Automate a task
Put Upstash to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Upstash works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Upstash to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1051ms average. Fast in production.
Upstash is checked daily against the live service.
- Fastest day
- 849ms
- Slowest day
- 1181ms
- 14-day trend
- Stable-2%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 23 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Upstash, so you can see the experience inside your AI.
It does not authenticate your account with Upstash. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Upstash Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_zagQBS4pH55ftq2YT6fVCqaAZsOFKu1bqXJWmxCc/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Upstash capabilities are ready to use.
{
"mcpServers": {
"upstash-mcp": {
"url": "https://edge.vinkius.com/vk_preview_zagQBS4pH55ftq2YT6fVCqaAZsOFKu1bqXJWmxCc/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Upstash in Claude and other AIs
Who it's for
Built for the work Upstash owners hand off.
This MCP is built for engineers who need to interact with live data without leaving their coding environment.
- 01
Backend Developers
Manage caching, feature flags, and session storage through chat.
- 02
DevOps Engineers
Monitor database health and manage data lifecycles via TTL.
- 03
Full-Stack Teams
Manipulate application state in Redis without using a CLI.
FAQ
Questions Upstash owners ask.
- 01
Do I need a Redis CLI installed?
No. This MCP communicates with Upstash via the REST API, so your AI client handles everything.
- 02
Which AI clients can use this MCP?
Any MCP-compatible client, including Claude, Cursor, and Windsurf.
- 03
Is it safe to delete keys through the AI?
The del capability is irreversible. You should be specific when asking your agent to remove data.
- 04
Can I run multiple commands at once?
Yes. The pipeline capability allows your agent to execute a batch of commands in a single request.
- 05
How do I manage data expiration?
You can use the expire capability to set a TTL or use the set capability with an expiry parameter.
- 06
Where do I find my Upstash REST URL and Token?
Log in to the Upstash Console, select your Redis database, and look for the REST API section. You'll find the HTTPS Endpoint (your REST URL, e.g. https://xxx-yyy-12345.upstash.io) and the Token value. Copy both and paste them here. There are two token types: Standard (full access) and Read-Only (read-only commands). Use Standard for full functionality.
- 07
What Redis commands are supported via the REST API?
The Upstash REST API supports most Redis commands including: Strings (GET, SET, DEL, EXISTS, EXPIRE, TTL, INCR, DECR), Hashes (HSET, HGET, HGETALL), Lists (LPUSH, RPUSH, LRANGE, LLEN), Sets (SADD, SMEMBERS, SISMEMBER, SREM), Keys (KEYS, TYPE, PING), and Pub/Sub (PUBLISH). The pipeline endpoint allows executing multiple commands in a single request. Blocking commands (BLPOP, BRPOP) and WATCH/UNWATCH are not supported.
- 08
Can I execute multiple commands atomically?
The pipeline capability sends multiple commands in a single HTTP request for efficiency, but it is NOT atomic. other commands may interleave between them. For atomic multi-command execution, Upstash supports the /multi-exec endpoint (same syntax as pipeline but guarantees atomicity). However, this MCP server currently exposes the standard pipeline capability for batch operations.
- 09
Is the Upstash REST API rate-limited?
Upstash does not enforce a fixed RPS limit. Instead, your plan defines a daily command limit. Each REST call counts as one command (or multiple commands if using pipeline). If you exceed your daily limit, commands will fail with a 400 error. Check your Upstash console for current usage. For high-throughput scenarios, consider using the pipeline endpoint to batch multiple commands into single HTTP requests.
Explore
More in Loved By Devs
Upstash Redis AI Connector
Equip your AI to directly query, manage, and manipulate key-value data structures inside your serverless Upsta
ViewHevo Data (ETL & Data Pipeline) AI Connector
Manage data pipelines via Hevo — list pipelines, monitor destinations, and track usage.
ViewLog Line Key-Value Parser AI Connector
Extracts structured data and character offsets from unstructured log lines.
ViewApify AI Connector
Run web scraping actors, collect structured data, and manage storage datasets for large-scale data extraction
View
Suggestions
Data Pipeline Prover AI Connector
A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi
ViewApify AI Connector
Run web scraping actors, collect structured data, and manage storage datasets for large-scale data extraction
ViewData.gov Catalog AI Connector
Access the official US Government open data catalog. Search thousands of datasets, organizations, and spatial
ViewAI Data Moat Valuation Engine AI Connector
Quantify the economic and strategic value of proprietary datasets.
View
Connect Upstash to Claude, Cursor, ChatGPT & more
