by upstash
Enables natural‑language interaction with Upstash services such as creating Redis databases, listing keys, managing backups, and retrieving usage statistics via the Model Context Protocol.
Provides an MCP server that bridges LLM clients with Upstash’s Redis‑based cloud platform, allowing commands expressed in plain language to be translated into Upstash API operations.
npx
:
npx @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY
For HTTP transport (useful for web apps):
npx @upstash/mcp-server@latest --transport http --port 3000 --email YOUR_EMAIL --api-key YOUR_API_KEY
mcpServers
section, either pointing to the local command or the HTTP endpoint.UPSTASH_EMAIL
and UPSTASH_API_KEY
.Q: Which Node version is required? A: Node.js 18 or newer.
Q: Can I run the server behind a firewall? A: Yes – use the HTTP transport on a custom port and configure your client to point to that endpoint.
Q: What if my shell cannot locate npx
?
A: Use the full path returned by which npx
and replace the npx
entry in the client config.
Q: How do I handle node version managers like nvm?
A: Provide the absolute path to the node
binary in the MCP configuration.
Q: Where can I find more troubleshooting help? A: See the MCP quick‑start troubleshooting guide or ask in the official Discord community.
Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an installer as well as an MCP Server for Upstash Developer API's.
This allows you to use any MCP Client to interact with your Upstash account using natural language, e.g.:
First, get your Upstash credentials:
Add this to your MCP client configuration:
{
"mcpServers": {
"upstash": {
"command": "npx",
"args": [
"-y",
"@upstash/mcp-server@latest",
"--email",
"YOUR_EMAIL",
"--api-key",
"YOUR_API_KEY"
]
}
}
}
Streamable HTTP Transport (for web applications):
Start your MCP server with the http
transport:
npx @upstash/mcp-server@latest --transport http --port 3000 --email YOUR_EMAIL --api-key YOUR_API_KEY
And configure your MCP client to use the HTTP transport:
{
"mcpServers": {
"upstash": {
"url": "http://localhost:3000/mcp"
}
}
}
Create a Dockerfile:
FROM node:18-alpine
WORKDIR /app
# Install the latest version globally
RUN npm install -g @upstash/mcp-server
# Expose default port if needed (optional, depends on MCP client interaction)
# EXPOSE 3000
# Default command to run the server
CMD ["upstash-mcp-server"]
Then, build the image using a tag (e.g., upstash-mcp
). Make sure Docker Desktop (or the Docker daemon) is running. Run the following command in the same directory where you saved the Dockerfile
:
docker build -t upstash-mcp .
Configure Your MCP Client:
Update your MCP client's configuration to use the Docker command.
Example for a claude_desktop_config.json:
{
"mcpServers": {
"upstash": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"UPSTASH_EMAIL=YOUR_EMAIL",
"-e",
"UPSTASH_API_KEY=YOUR_API_KEY",
"upstash-mcp"
]
}
}
}
Note: This is an example configuration. Please refer to the specific examples for your MCP client (like Cursor, VS Code, etc.) earlier in this README to adapt the structure (e.g., mcpServers
vs servers
). Also, ensure the image name in args
matches the tag used during the docker build
command.
Your mcp client might have trouble finding the right binaries because of the differences between your shell and system PATH
.
To fix this, you can get the full path of the binaries by running which npx
or which docker
in your shell, and replace the npx
or docker
command in the MCP config with the full binary path.
If you are using a node version manager like nvm or fnm, please check this issue. You should change the node
command in the MCP config to the absolute path of the node binary.
See the troubleshooting guide in the MCP documentation. You can also reach out to us at Discord.
redis_database_create_backup
redis_database_create_new
redis_database_delete
redis_database_delete_backup
redis_database_get_details
redis_database_list_backups
redis_database_list_databases
redis_database_reset_password
redis_database_restore_backup
redis_database_run_multiple_redis_commands
redis_database_run_single_redis_command
redis_database_set_daily_backup
redis_database_update_regions
redis_database_get_usage_last_5_days
redis_database_get_stats
Clone the project and run:
pnpm install
pnpm run watch
This will continuously build the project and watch for changes.
For testing, you can create a .env
file in the same directory as the project with the following content:
UPSTASH_EMAIL=<UPSTASH_EMAIL>
UPSTASH_API_KEY=<UPSTASH_API_KEY>
This will be used for setting the Claude config.
To install the Claude Desktop config for local development, add the following to your Claude Desktop MCP config:
{
"mcpServers": {
"upstash": {
"command": "node",
"args": [
"<path-to-repo>/dist/index.js",
"run",
"--email",
"<UPSTASH_EMAIL>",
"--api-key",
"<UPSTASH_API_KEY>"
]
}
}
}
NOTE: The same issue with node version manager applies here. Please look at the note in the usage section if you are using a node version manager.
You can now use Claude Desktop to run Upstash commands.
To view the logs from the MCP Server in real time, run the following command:
pnpm run logs
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "upstash": { "command": "npx", "args": [ "-y", "@upstash/mcp-server@latest", "--email", "YOUR_EMAIL", "--api-key", "YOUR_API_KEY" ], "env": {} } } }
Discover more MCP servers with similar functionality and use cases
by daytonaio
Provides a secure, elastic sandbox environment for executing AI‑generated code with isolated runtimes and sub‑90 ms provisioning.
by awslabs
Specialized servers that expose AWS capabilities through the Model Context Protocol, allowing AI assistants and other applications to retrieve up‑to‑date AWS documentation, manage infrastructure, query services, and perform workflow automation directly from their context.
by awslabs
AWS MCP Servers allow AI agents to interact with and manage a wide range of AWS services using natural language commands. They enable AI-powered cloud management, automated DevOps, and data-driven insights within the AWS ecosystem.
by cloudflare
Remote Model Context Protocol endpoints that let AI clients read, process, and act on data across Cloudflare services such as Workers, Radar, Observability, and more.
by supabase-community
Enables AI assistants to interact directly with Supabase projects, allowing them to query databases, fetch configuration, manage tables, and perform other project‑level operations.
by Azure
azure-mcp is a server that implements the Model Context Protocol (MCP) to connect AI agents with Azure services. It allows developers to interact with Azure resources like Storage, Cosmos DB, and the Azure CLI using natural language commands within their development environment.
by Flux159
MCP Server for Kubernetes management commands, enabling interaction with Kubernetes clusters to manage pods, deployments, and services.
by strowk
Provides a Golang‑based server that enables interaction with Kubernetes clusters via prompts, allowing listing of contexts, namespaces, resources, nodes, pods, events, logs, and executing commands inside pods.
by jamsocket
Run arbitrary Python code securely in persistent, stateful sandboxes that remain available indefinitely.