Upstash Redis Connector for AI agents.
7 live capabilities
Manage serverless Redis data and cache keys directly from your chat.
Waiting for input…
Why people use Upstash Redis
Upstash Redis for Faster Cache Debugging
With this Connector, you just tell your agent to find all keys starting with 'session:' and check the expiration times. It pulls the data, summarizes the status, and lets you delete the broken ones right there in the chat. You stay in your flow while the agent does the data hunting.
What Vinkius changes
You get a conversational interface for your serverless Redis data.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a session error
A user reports a session drop.
- Real-world use case 02
Adjusting rate limits
Rate limits are being hit too early.
- Real-world use case 03
Clearing a bloated cache
The cache is getting too large.
Complete set · 7capabilities
The complete Upstash Redis capability set.
These are the exact actions your AI can choose when you ask it to work with Upstash Redis.
01—04
4 capabilities in this set.
Part of 7 available through Upstash Redis.
- 01 Capability
Delete
Remove one or more keys from your database. This is the fastest way to clear out specific cache fragments or expired data.
- 02 Capability
Increment
Increase or decrease a numerical value at a specific key. It's perfect for managing counters like hit limits or request tallies.
- 03 Capability
Get key info
Retrieve the data type and remaining TTL for a specific key. This helps you understand how your database is currently storing a piece of data.
- 04 Capability
List keys
Scan your database for keys matching a specific glob pattern. This helps you find specific data without pulling every key into memory.
05—07
3 capabilities in this set.
Part of 7 available through Upstash Redis.
- 05 Capability
Ping
Check if your Redis instance is online and responsive. Use this to quickly verify connectivity during setup or troubleshooting.
- 06 Capability
Set
Create or update a string value in your database. You can also set a Time-To-Live (TTL) to control how long the data stays active.
- 07 Capability
Get
Fetch the raw string value associated with a specific key. Use this to inspect the actual content of your stored data.
Set up in minutes
One URL. Then ask Upstash Redis to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Upstash Redis from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Upstash Redis, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Upstash Redis for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Upstash Redis URL.
- Step 03
Save and start
Save the connection and enable Upstash Redis in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"upstash-redis": {
"url": "https://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Upstash Redis
Open Agent mode in chat and ask: "Using Upstash Redis, help me...". 7 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"upstash-redis": {
"url": "https://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Upstash Redis
Ask Copilot: "Using Upstash Redis, help me...". 7 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"upstash-redis": {
"url": "https://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Upstash Redis
Open Cascade and ask: "Using Upstash Redis, help me...". 7 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"upstash-redis": {
"url": "https://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Upstash Redis
Ask Cline: "Using Upstash Redis, help me...". 7 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add upstash-redis --transport http "https://edge.vinkius.com/vk_preview_LWIxSXPx9aBN8ImAGEwBNh9Bp3KqtBybpfNFxgJc/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Upstash Redis
Ask Claude: "Using Upstash Redis, show me...". 7 tools are ready
Where the request belongs
Work Upstash Redis can move forward.
This is for the engineers who are tired of context-switching. If you're constantly jumping into a database UI to debug a production cache issue or manually clearing out old sessions during a deployment, this is for you.
Backend Developer
Debugging session persistence and clearing stale cache during development.
DevOps Engineer
Checking rate-limiting counters and instance health during live incidents.
System Architect
Auditing TTL behaviors and eviction policies for new features.
When one Connector is not enough
Carry the request into a workflow.
Combine Upstash Redis with the systems that finish the task.
View all recipesBuild the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsUpstash
Manage serverless Redis via Upstash REST API. execute commands, manage data structures and monitor your database from any AI agent.
Xata
Automate your serverless database workflows with Xata. manage organizations, projects, and branches directly from your AI agent.
Aiven
Manage Aiven cloud infrastructure. provision databases, manage projects, and monitor services directly from your AI agent.
QStash (Serverless Message Queue)
Manage serverless messaging, task scheduling, and webhooks via Upstash QStash. publish messages, manage queues, and handle DLQs directly.
Appwrite
Open-source backend-as-a-service. manage databases, storage, and users via AI.
Xata (Serverless DB)
Manage your serverless databases via Xata. list organizations, manage projects, branches, and execute SQL queries directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Upstash Redis connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Upstash Redis.
The practical details behind the request, access and result.
Can the Upstash Redis MCP help me clear my cache?
Yes, it lets your agent delete specific keys or groups of keys using patterns. You can just ask it to clear out old data or specific cache fragments.
How do I use Upstash Redis MCP to manage user sessions?
Your agent can read, write, and set expiration times on session keys automatically. This makes it easy to check if a user is logged in or to manually refresh a session.
Does Upstash Redis MCP support rate limiting?
It can increment and decrement numerical counters, which is perfect for managing request limits. You can ask your agent to bump a counter or check the current limit.
Can I check my database health with Upstash Redis MCP?
Yes, the agent can ping your instance to verify that it is online and reachable. This is a quick way to check connectivity during a deployment or a debug session.
Is Upstash Redis MCP good for debugging?
It is excellent for quickly inspecting key values and expiration times without leaving your terminal. It helps you see exactly what is stored in your cache at any moment.
How does Upstash Redis MCP handle data expiration?
You can use the set command to give every new key a specific Time-To-Live in seconds. This ensures your database doesn't get cluttered with old data.
Where do I locate my Upstash REST URL and Token?
Sign into your Upstash management console and load your specific Redis cluster. Scroll down visually on the main 'Details' page until you hit the 'REST API' section block. You will see both your 'UPSTASH_REDIS_REST_URL' and the alphanumeric 'UPSTASH_REDIS_REST_TOKEN' ready to be copied.
Can the agent interact with standard Redis connections (redis://)?
No, this specific MCP connection module specifically utilizes Upstash's serverless HTTP/REST endpoints. It bypasses conventional persistent TCP Redis sockets to provide highly secure and connection-agnostic read/write integrations optimized for AI servers.
Are there limitations to wildcard patterns when doing list_keys?
Yes, standard Redis operational caveats apply. Searching broadly via a '' (asterisk) scan across massively populated environments isn't recommended. Aim to request the AI narrow down patterns, like 'session:' instead of blank wildcards.
One connection away
Give your agent a direct line to Upstash Redis.
Connect Upstash Redis once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available