Upstash

Upstash
Official

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.

upstash

AI Integration Systems
Visit Server

Tools

redis_database_create_new

Create a new Upstash redis database. NOTE: Ask user for the region and name of the database. NOTE: Don't show the database ID from the response to the user unless explicitly asked or needed.

redis_database_delete

Delete an Upstash redis database.

redis_database_list_databases

List all Upstash redis databases. Only their names and ids. NOTE: Don't show the database ID from the response to the user unless explicitly asked or needed.

timestamps_to_date

Use this tool to convert a timestamp to a human-readable date

redis_database_run_multiple_redis_commands

Run multiple Redis commands on a specific Upstash redis database

redis_database_run_single_redis_command

Run a single Redis command on a specific Upstash redis database. NOTE: For discovery, use SCAN over KEYS. Use TYPE to get the type of a key. NOTE: SCAN cursor [MATCH pattern] [COUNT count] [TYPE type]

redis_database_get_details

Get further details of a specific Upstash redis database. Includes all details of the database including usage statistics. db_disk_threshold: Total disk usage limit. db_memory_threshold: Maximum memory usage. db_daily_bandwidth_limit: Maximum daily network bandwidth usage. db_request_limit: Total number of commands allowed. All sizes are in bytes NOTE: Don't show the database ID from the response to the user unless explicitly asked or needed.

redis_database_update_regions

Update the read regions of an Upstash redis database.

redis_database_reset_password

Reset the password of an Upstash redis database.

redis_database_get_usage_last_5_days

Get PRECISE command count and bandwidth usage statistics of an Upstash redis database over the last 5 days. This is a precise stat, not an average. NOTE: Ask user first if they want to see stats for each database seperately or just for one.

redis_database_get_stats

Get SAMPLED usage statistics of an Upstash redis database over a period of time (1h, 3h, 12h, 1d, 3d, 7d). Use this to check for peak usages and latency problems. Includes: read_latency_mean, write_latency_mean, keyspace, throughput (cmds/sec), diskusage NOTE: If the user does not specify which stat to get, use throughput as default.

redis_database_create_backup

Create a backup of a specific Upstash redis database. NOTE: Ask user to choose a name for the backup

redis_database_delete_backup

Delete a backup of a specific Upstash redis database.

redis_database_restore_backup

Restore a backup of a specific Upstash redis database. A backup can only be restored to the same database it was created from.

redis_database_list_backups

List all backups of a specific Upstash redis database.

redis_database_set_daily_backup

Enable or disable daily backups for a specific Upstash redis database.

README

Upstash MCP Server

smithery badge

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.:

  • "Create a new Redis database in us-east-1"
  • "List my databases"
  • "List keys starting with "user:" in users-db"
  • "Create a backup"
  • "Give me the spikes in throughput during the last 7 days"

Usage

Requirements

How to use locally

Installing for Claude Desktop

To install Upstash MCP Server for Claude Desktop automatically via Smithery run the following command:

npx -y @smithery/cli@latest install @upstash/mcp-server --client claude

<details> <summary>Install without Smithery</summary>

npx @upstash/mcp-server init <UPSTASH_EMAIL> <UPSTASH_API_KEY>

This will edit your MCP config file and add an entry for Upstash.

</details>

Installing for Cursor

To install Upstash MCP Server for Cursor automatically via Smithery run the following command:

npx -y @smithery/cli@latest install @upstash/mcp-server --client cursor

<details> <summary>Install without Smithery</summary>

Add the following command to the MCP config in Cursor. For more info, check the Cursor MCP docs.

npx -y @upstash/mcp-server run <UPSTASH_EMAIL> <UPSTASH_API_KEY>

</details>

Installing for Windsurf

To install Upstash MCP Server for Windsurf automatically via Smithery run the following command:

npx -y @smithery/cli@latest install @upstash/mcp-server --client windsurf

<details> <summary>Install without Smithery</summary>

Add the following command to the MCP config in Windsurf. For more info, check out the Windsurf MCP docs.

npx -y @upstash/mcp-server run <UPSTASH_EMAIL> <UPSTASH_API_KEY>

</details>

Running with Docker

You can also use the provided Docker image to run the server.

docker build -t upstash-mcp .

# Run the stdio server, add this command to you MCP config
docker run --rm -i \
  -e UPSTASH_EMAIL=<UPSTASH_EMAIL> \
  -e UPSTASH_API_KEY=<UPSTASH_API_KEY> \
  upstash-mcp

Troubleshooting

Common Issues

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.

Node Version Manager

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.

Additional Troubleshooting

See the troubleshooting guide in the MCP documentation. You can also reach out to us at Discord.

Tools

Redis

  • 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

Development

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 and running mcp inspector.

Testing with Claude Desktop

To install the Claude Desktop config for local development, run the following command:

pnpm run setup

This will add an upstash entry to your MCP config file that points to the local build of the package.

{
  "upstash": {
    "command": "node",
    "args": ["<path-to-repo>/dist/index.js", "run", "<UPSTASH_EMAIL>", "<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

Testing with MCP Inspector

You can also use the MCP Inspector to test the tools.

pnpm run inspector

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
AIO-MCP Server

AIO-MCP Server

🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from

Featured
Local
React MCP

React MCP

react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts

Featured
Local
Atlassian Integration

Atlassian Integration

Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.

Featured
Any OpenAI Compatible API Integrations

Any OpenAI Compatible API Integrations

Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.

Featured
MySQL Server

MySQL Server

Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.

Featured
Browser Use (used by Deploya.dev)

Browser Use (used by Deploya.dev)

AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.

Featured
Aindreyway Codex Keeper

Aindreyway Codex Keeper

Serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices.

Featured