Skip to main content

Upstash ships Skills, a CLI, an MCP server, and llms.txt so your agent can build on and manage Redis, QStash, Workflow, Vector, Search, and Box. Set them all up with one command, or pick your agent for step-by-step instructions.

Set up with one command#

Run this in your terminal:

It detects Claude Code, Codex, Cursor, Gemini CLI, VS Code, GitHub Copilot CLI, and OpenCode, and lets you pick which to set up. Each one gets the Upstash MCP server and skills: as the Upstash plugin where the agent supports plugins, otherwise written into its config. The MCP server signs in with OAuth on first use. See the CLI page for flags.

Pick your agent#

Claude Code
Anthropic's terminal and IDE agent. The marketplace plugin bundles the skills and the remote MCP over OAuth.
Cursor
AI code editor. One-click MCP install button; skills via the Agent Skills CLI.
OpenAI Codex
OpenAI's coding agent. The Codex plugin bundles the skills and the remote MCP over OAuth.
OpenCode
Open-source terminal agent that loads Agent Skills natively. MCP via its config.
Zed
Editor with a built-in Agent Panel. Skills via the CLI, MCP via settings.json.
GitHub Copilot
Copilot agent mode in VS Code. MCP via .vscode/mcp.json.
Devin Desktop
Cognition's desktop agent workspace and IDE. Skills via the CLI, MCP via its config file.
Gemini CLI
Google's open-source terminal agent. The extension bundles the skills and the remote MCP over OAuth.
Google Antigravity
Google's agent-first IDE. Skills via the CLI, MCP via the Antigravity MCP config.
DeepSeek Harness
One bundle installs the skills and the MCP server. Log in once from a session.
Claude Desktop
Anthropic's desktop app. The marketplace plugin bundles the skills and the remote MCP over OAuth.
Grok
xAI's Grok Build agent. Skills via the Agent Skills CLI, MCP via grok mcp add.

Don’t see your agent? See the full list of agents.

Resources#

Skills

Docs and CLI reference for every Upstash SDK, loaded on demand.

MCP Server

Live tools to query, debug, and manage your Upstash account.

CLI

Agent-friendly terminal for managing resources. JSON output, dry runs.

llms.txt

The docs as plain text for tools without skill or MCP support.

Set up by hand#

Install the Upstash skill. It includes the upstash CLI reference, so this one step is enough for most workflows:

To let your agent read and change your account directly, add the MCP server. The remote server needs nothing installed — connect over HTTP and approve the OAuth consent on first use (shown here for Claude Code):

Prefer a headless setup, or need Upstash Box tools? Run the local server with a Developer API key:

See the MCP server page for remote vs. local, authentication, and feature options.

Note

Only working against a single Redis database? The lightweight Redis MCP needs just that database’s REST URL and token, not an account API key.

Building AI into your app?#

The resources above are for agents that help you build. If you’re building agents or AI features into your own product, start here:

Agent memory & chat history

Long-term memory, RAG, and chat history for the Vercel AI SDK and Eve, backed by Redis.

Vector

Embeddings and semantic search for RAG pipelines, with LangChain, LlamaIndex, and AI SDK integrations.

Workflow Agents

Durable multi-agent orchestration with retries and no timeouts. Works with AI SDK and LangChain tools.

Box

Sandboxed cloud containers with Claude Code, Codex, or OpenCode built in, for running agents at scale.

Search

Full-text and semantic search over your documents, ready to serve as a retrieval tool.

QStash for LLM calls

Call LLM APIs with retries, callbacks, batching, and a 2-hour timeout from serverless runtimes.