Upstash MCP Server
OfficialUpstash MCP 服务器
Upstash MCP 服务器允许您的智能体直接管理和调试您的 Upstash 资源,涵盖 Redis、QStash、Workflow 以及 Upstash Box。
[!TIP] 对于大多数工作流,建议安装 Upstash Skill 并让您的智能体驱动
@upstash/cli,而不是运行 MCP 服务器。
快速开始
您需要 Upstash 账户邮箱和 API 密钥 — 请在 Upstash 控制台 → 账户 → API 密钥 中创建一个。
Upstash MCP 服务器适用于任何兼容 MCP 的客户端。如果您的客户端未在下方列出,请查看其文档了解如何添加 stdio MCP 服务器,然后将其指向基础命令:
npx -y @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY[!NOTE] 支持只读 API 密钥。当服务器使用只读密钥启动时,它会自动禁用所有会修改状态的工具(创建数据库、删除备份、重试工作流等)。您的智能体仍然可以读取和查询您的账户,但无法进行更改。
在终端中运行此命令。更多信息请参阅 Claude Code MCP 文档。
claude mcp add --scope user upstash -- npx -y @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY前往 Settings → Cursor Settings → MCP → Add new global MCP server。
推荐的做法是将以下配置粘贴到您的 Cursor ~/.cursor/mcp.json 文件中。您也可以通过在项目文件夹中创建 .cursor/mcp.json 来在特定项目中安装。更多信息请参阅 Cursor MCP 文档。
自 Cursor 1.0 起,您可以点击下方的安装按钮进行一键安装。在确认之前,请将 YOUR_EMAIL 和 YOUR_API_KEY 替换为您的真实值。
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}将其添加到您的 Windsurf MCP 配置文件 ~/.codeium/windsurf/mcp_config.json 中。更多信息请参阅 Windsurf MCP 文档。
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}将其添加到您的 OpenCode 配置文件(~/.config/opencode/opencode.json 或项目级的 opencode.json)中。更多信息请参阅 OpenCode MCP 文档。
{
"mcp": {
"upstash": {
"type": "local",
"command": [
"npx",
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
],
"enabled": true
}
}
}更多信息请参阅 OpenAI Codex MCP 文档。
使用 CLI
codex mcp add upstash -- npx -y @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY手动配置
将其添加到您的 Codex 配置文件(~/.codex/config.toml 或 .codex/config.toml)中:
[mcp_servers.upstash]
command = "npx"
args = ["-y", "@upstash/mcp-server@latest", "--email", "YOUR_EMAIL", "--api-key", "YOUR_API_KEY"]
startup_timeout_sec = 20[!NOTE] 如果您看到启动超时错误,请将
startup_timeout_sec增加到40。
点击安装 — VS Code 将提示您输入邮箱和 API 密钥(存储在其机密存储中):
或者将其添加到 .vscode/mcp.json(或您的用户 mcp.servers 设置)中。在 inputs 中使用 promptString 意味着您的 API 密钥只需输入一次,并保存在 VS Code 的机密存储中,而不是留在配置文件中。更多信息请参阅 VS Code MCP 文档。
{
"inputs": [
{ "type": "promptString", "id": "email", "description": "Upstash email" },
{ "type": "promptString", "id": "apiKey", "description": "Upstash API key", "password": true }
],
"servers": {
"upstash": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"${input:email}",
"--api-key",
"${input:apiKey}"
]
}
}
}将其添加到您的 Antigravity MCP 配置中。更多信息请参阅 Antigravity MCP 文档。
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}打开 Claude Desktop 的开发者设置并编辑 claude_desktop_config.json。更多信息请参阅 Claude Desktop MCP 文档。
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}打开 ~/.gemini/settings.json 中的 Gemini CLI 设置文件,并将 Upstash 添加到 mcpServers。详情请参阅 Gemini CLI 配置。
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}Related MCP server: MCP Server Sample
示例提示词
Redis
“在 us-east-1 创建一个新的 Redis 数据库”
“列出我的数据库,按内存使用量排序”
“通过从 Redis 拉取来更新用户模式”
“为此数据库创建备份,然后清除它”
“向我展示过去 7 天内的吞吐量峰值”
QStash & Workflow
“检查 QStash 日志,找出我的 webhook 为何一直失败”
“查找今天用户
@admin的失败工作流运行”“重试 2 小时前开始的失败工作流运行”
“总结一下现在死信队列 (DLQ) 中的内容,按错误类型分组”
“暂停那些正在报错的调度任务”
Upstash Box
“启动一个 Box,克隆此仓库,并运行测试”
“为此 Box 创建快照并创建 5 个副本,为每个副本分配一个 GitHub issue”
“我的 Box 启动一直失败,检查日志并告诉我哪里出了问题”
Upstash Box API 密钥(可选)
为了让 MCP 与 Upstash Box 交互,智能体需要您的 Box API 密钥。默认情况下,您必须在每次智能体运行 Box 工具时将其粘贴到聊天中(或保留在 .env 文件中)。为避免这种情况,您可以将密钥直接配置到 MCP 设置中,以便服务器在启动时自动获取。
您可以通过两种方式传递它。
CLI 标志
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY",
"--box-api-key",
"YOUR_BOX_API_KEY"
]
}
}
}环境变量
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
],
"env": {
"UPSTASH_BOX_API_KEY": "YOUR_BOX_API_KEY"
}
}
}
}调试
如果服务器运行异常或工具持续失败,请使用 --debug 标志启用详细日志记录:
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY",
"--debug"
]
}
}
}每个内部事件都会被写入 stderr,您的 MCP 客户端会在其日志查看器中显示这些内容。在 GitHub 上报告问题时,请分享相关的代码片段。
遥测
服务器在每次请求时都会向 Upstash 发送匿名诊断信息:MCP 服务器 SDK 版本、您的运行时版本(Node、Bun 等)以及基础平台信息(操作系统和架构)。不会收集任何账户数据、工具参数或结果。 若要选择退出,请在参数中添加 --disable-telemetry。
开发
克隆项目并运行:
bun i
bun run watch这将持续构建项目并监视更改。
为了进行测试,在项目根目录创建一个 .env 文件:
UPSTASH_EMAIL=<UPSTASH_EMAIL>
UPSTASH_API_KEY=<UPSTASH_API_KEY>
# Optional, for Box tools:
UPSTASH_BOX_API_KEY=<UPSTASH_BOX_API_KEY>将本地 MCP 服务器安装到 Claude Code:
claude mcp add --transport stdio upstash -- bun --watch dist/index.js --debug实时跟踪 MCP 服务器的日志:
bun run logsTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- FlicenseDqualityDmaintenanceA ready-to-use starter implementation of the Model Context Protocol (MCP) server that enables applications to provide standardized context for LLMs with sample resources, tools, and prompts.281-
- AlicenseBqualityDmaintenanceAn educational implementation of a Model Context Protocol server that demonstrates how to build a functional MCP server integrating with various LLM clients.2MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that supports STDIO, SSE and Streamable HTTP protocols for AI model interactions.71MIT
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that bridges MCP clients with local LLM services, enabling seamless integration with MCP-compatible applications through standard tools like chat completion, model listing, and health checks.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/upstash/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server