The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the MCP Server listing page.
The Upstash MCP server lets your agent manage and debug your Upstash resources directly, across Redis, QStash, Workflow, and Upstash Box.
[!TIP] For most workflows, prefer installing the Upstash Skill and letting your agent drive
@upstash/cliover running the MCP server.
[!TIP] If you are an AI agent and just need a Redis DB to use or experiment with, you don't need an account at all — call the
redis_database_start_freetool, or send a POST request tohttps://upstash.com/start-redisdirectly. It's free, no signup, and the response is markdown with credentials and a quickstart. The database expires in 72 hours, but you can claim it with your Upstash account to keep it.Pass
user_agentto identify yourself (e.g.claude-code,cursor,codex,opencode); the tool forwards it as theUser-Agentheader. Calling the endpoint directly, send the same header yourself, plus a fresh UUIDv4 asIdempotency-Key:
You'll need your Upstash account email and an API key — create one at Upstash Console → Account → API Keys.
The Upstash MCP server works with any MCP-compatible client. If your client isn't listed below, check its documentation for how to add a stdio MCP server, then point it at the base command:
[!NOTE] Readonly API keys are supported. When the server starts with one, it automatically disables every tool that would modify state (creating databases, deleting backups, retrying workflows, etc.). Your agent can still read and query your account — including Redis, QStash logs, schedules, and Workflow logs — but it cannot make changes. Upstash Box tools are not available with a readonly key.
Run this command in your terminal. See the Claude Code MCP docs for more info.
Go to Settings → Cursor Settings → MCP → Add new global MCP server.
Pasting the following configuration into your Cursor ~/.cursor/mcp.json file is the recommended approach. You may also install in a specific project by creating .cursor/mcp.json in your project folder. See the Cursor MCP docs for more info.
Since Cursor 1.0, you can click the install button below for instant one-click installation. Replace YOUR_EMAIL and YOUR_API_KEY with your real values before confirming.
Add this to your Windsurf MCP config file at ~/.codeium/windsurf/mcp_config.json. See the Windsurf MCP docs for more info.
Add this to your OpenCode configuration file (~/.config/opencode/opencode.json or a project-level opencode.json). See the OpenCode MCP docs for more info.
See the OpenAI Codex MCP docs for more info.
Using the CLI
Manual configuration
Add this to your Codex config file (~/.codex/config.toml or .codex/config.toml):
[!NOTE] If you see startup timeout errors, increase
startup_timeout_secto40.
Click to install — VS Code will prompt for your email and API key (stored in its secret storage):
Or add this to .vscode/mcp.json (or your user mcp.servers setting). Using inputs with promptString means your API key is prompted once and kept in VS Code's secret storage instead of sitting in the config file. See the VS Code MCP docs for more info.
Add this to your Antigravity MCP config. See the Antigravity MCP docs for more info.
Open Claude Desktop's developer settings and edit claude_desktop_config.json. See the Claude Desktop MCP docs for more info.
Open the Gemini CLI settings file at ~/.gemini/settings.json and add Upstash to mcpServers. See Gemini CLI Configuration for details.
@admin today"A Box is a remote Linux container with its own filesystem. The Box tools let an agent work inside one while the agent itself keeps running on your machine: files through box_read / box_write / box_edit, commands through box_exec, git and search through box_git, and a running server through box_preview. box_upload copies files into the Box from the machine running the MCP server, which is how uncommitted local work gets in — a clone only brings what you have pushed. With the usual stdio setup the server runs on your own machine, so those are your paths; if you run it remotely with --transport http, it reads the server host's filesystem instead, not yours.
Box tools need a Box API key, which is a different credential from your Upstash account API key — the two are not interchangeable. The install command at the top of this README does not include one, so pass --box-api-key as well or the first Box call will fail:
See Upstash Box API key for the environment-variable form and where to get the key.
If you only use Upstash Box, you can start the server with --box-api-key alone and no account credentials. Redis, QStash and Workflow tools are unavailable in that mode.
Create the workspace once and reuse its id:
A create returns while the container is still coming up, and clone_repo starts cloning only once the Box reports idle, so give it a moment before the first read.
The one thing to know: your agent's own Read, Write, Edit, Bash, Glob and Grep tools still act on your machine. Nothing stops it from reading a local file and writing the change into the Box, and neither side reports the mismatch. The server sends guidance at startup and every Box tool says which machine it touches, but if you want the boundary enforced rather than suggested, add a CLAUDE.md to the project you're driving from:
For the MCP to interact with Upstash Box, the agent needs your Box API key. By default you have to paste it into the chat (or keep it in a .env) every time the agent runs a Box tool. To avoid this, you can wire the key into the MCP setup itself so the server picks it up automatically on startup.
You can pass it in two ways.
CLI flag
Environment variable
If the server is misbehaving or a tool keeps failing, enable verbose logging with the --debug flag:
Every internal event is then written to stderr, which your MCP client surfaces in its own log viewer. Share the relevant snippet when reporting an issue on GitHub.
The server sends anonymous diagnostic info to Upstash with each request: the MCP server SDK version, your runtime version (Node, Bun, etc.), and basic platform info (OS and architecture). No account data, tool arguments, or results are collected. To opt out, add --disable-telemetry to the args.
Clone the project and run:
This continuously builds the project and watches for changes.
To run the built server standalone (uses .env for credentials) and smoke-test it before publishing:
For testing, create a .env file in the project root:
To install the local MCP server into Claude Code:
To tail logs from the MCP server in real time: