Upstash MCP connector
The Upstash connector brings your Redis databases, backups, QStash schedules, message queues and vector indexes to Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent, so each person works with them under their own access and every action is logged.
- Connects over OAuth
- Free 14-day trial
- No credit card
Which Redis databases have no backup from this week?
Working in Upstash with Elaichi
-
Redis list databases
-
Redis get database
-
Redis get stats
How to connect Upstash to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
Upstash MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Upstash MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
Upstash MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
Upstash MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Upstash MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect Upstash to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with Upstash through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Upstash is logged.
-
Platform
Check a Redis database before a launch
Ask for memory use, request counts and eviction settings on the database behind tomorrow's release, and get a plain answer without opening the console.
-
Engineering
Take a backup before a risky change
Have the agent create a backup of the sessions database, confirm it finished, and list the recent backups so you know there is something to roll back to.
-
Operations
Clear the dead letter queue after an outage
See which messages landed in the dead letter queue overnight, decide what to retry or drop, and clear it once the downstream service is back.
-
Engineering
Pause a QStash schedule for the weekend
Pause the nightly export schedule before a maintenance window, then resume it on Monday, without hunting for the schedule in the dashboard.
-
Data
See what a vector index holds
Ask how many vectors are in the product search index, what dimension it uses, and when it was last updated before you point a new feature at it.
-
Support
Trace a failed message through the logs
When a customer reports a missing webhook, pull the QStash logs for that message and find out whether it was delivered, retried or dropped.
Try asking
- “Which Redis databases have no backup from this week?”
- “Show me what is sitting in the dead letter queue.”
- “Pause the nightly report schedule in QStash until Monday.”
What connecting Upstash gets you
6 screens from Elaichi, each doing one job for your Upstash account.
Ask Elaichi to work across your apps.
Which Redis databases have no backup from this week?
Show me what is sitting in the dead letter queue.
Pause the nightly report schedule in QStash until Monday.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about your Redis databases in plain language.
Answers come from live Upstash databases, backups and QStash schedules, not from a stale export.
Copy the endpoint
AI apps
One endpoint brings Upstash to every client.
Claude, ChatGPT, Cursor and Microsoft Copilot connect over OAuth, with no SDK and no shared API key.
Tool catalog
55 Upstash tools, ready without writing code.
Databases, backups, QStash schedules, dead letter queues and vector indexes, covered with no custom code.
Toolboxes
Each team gets its own Upstash toolbox.
Platform keeps database management, operations keeps queues, and nobody sees more than their job needs.
Shared connections
Share one Upstash connection, never a credential.
Teammates work through the shared account while the credential stays with the person who connected it.
Audit log
Every Upstash action is logged with a name.
See who deleted a database, cleared a queue or changed a schedule, and when.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
Upstash digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch databases
Upstash
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
Upstash
Queued
Workflows
A schedule fires and the digest gets written.
Upstash databases are fetched, grouped and summarized, a person approves, then it posts back.
Upstash health
Refreshed 4 minutes ago · every 15 minutes · from the databases collection
Databases
1,284 ↓ 12%
Backups
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Databases created
Last 14 days
By team
Share of activity
Platform 34%
Production 27%
Staging 21%
Operations 18%
Collections and dashboards
Upstash health numbers arrive without anyone asking.
Four metrics, 14 days of databases created and a team breakdown, refreshed with no model involved.
Why connect Upstash's MCP server through Elaichi
Upstash builds and runs this MCP server. Elaichi sits in front of it, so Upstash's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to Upstash's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT, Cursor and Microsoft Copilot reach Upstash's tools at the same Elaichi address as every other connected app. Nobody adds Upstash's server to each client one by one.
-
Each person signs in as themselves
Each person signs in to Elaichi as themselves. Members connect with their own Upstash sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.
-
Rules checked before a call leaves
Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches Upstash's server. By default, a tool Upstash does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.
-
One audit log for every app
Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.
-
Tool issues go to Upstash
Upstash builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Upstash team.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for Upstash
All three can connect Upstash to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Upstash tools | Allow or restrict single Upstash tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Upstash call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
Upstash tools for your AI agents
55 tools are ready to call through Elaichi's MCP endpoint the moment you connect Upstash, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Upstash builds and runs these tools.
No tools match your search.
Questions, answered
How do I connect Upstash to Claude?
Connect Upstash in Elaichi first, signing in to your Upstash account over OAuth with no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Claude asks you to sign in to Elaichi and your Upstash connection is ready to use.
Does Upstash work with ChatGPT and Cursor as well as Claude?
Yes. Once Upstash is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Upstash once and every client picks it up.
What can an AI agent actually do with my Upstash data?
An agent connected to Upstash can list your Redis databases, report their memory and request stats, take or list backups, create or rename a database, and run a command against one. It can also publish messages and manage schedules in QStash, read logs, clear a dead letter queue, and tell you what a vector index holds. Short concrete asks work best, such as 'back up the sessions database' rather than a long paragraph.
Does connecting Upstash give the AI access to every database in my account?
No more than you already have. The AI works inside the Upstash access of the person who signed in, so it sees only the databases, schedules and indexes that person can see. Elaichi can narrow that further with roles and restrictions, and it never widens it.
Can I stop an agent from deleting or changing things in Upstash?
Yes. Restrictions in Elaichi apply per action, so you can allow reading database stats and listing backups while restricting deleting a database, changing eviction settings or clearing a queue. A restricted Upstash action still appears in Elaichi's tool search, flagged as restricted, but the AI client cannot run it, whatever the prompt says.
What happens to an Upstash connection when someone leaves?
Offboarding that person in Elaichi ends their access to Upstash through every client at once. A shared Upstash connection keeps working for everyone else on the team. If you want the connection gone entirely, disconnect Upstash once in Elaichi and it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.
Does the Upstash MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Upstash is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Upstash?
Yes. Both let Claude, ChatGPT or Cursor use Upstash. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Upstash call.
How is Elaichi different from Composio for Upstash?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Upstash: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Upstash in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot