pickfit

BrowseMCP servers

Redis MCP Server

An MCP server that lets AI agents store, manage and search data in Redis through natural language.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.14
  1. uv tool install redis-mcp-server (0.5.1)

    uv tool install redis-mcp-server

Check that it works

redis-mcp-server --help

The output should contain “Redis MCP Server - Model Context Protocol server for Redis.”.

Add it to your agent

claude mcp add mcp-redis -- redis-mcp-server --url redis://localhost:6379/0
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "mcp-redis": {
      "command": "redis-mcp-server",
      "args": [
        "--url",
        "redis://localhost:6379/0"
      ]
    }
  }
}

Add redis-mcp-server as an MCP server in your AI client, pointed at your Redis instance, and its Redis tools become available to the agent.

What it does

  • Query and update Redis in plain language
    Not tested
  • Manage hashes, lists, sets, streams and more
    Not tested
  • Manage vector indexes and run vector search
    Not tested
  • Sign in to Azure Managed Redis with EntraID
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 4 features work
  4. Works offline

Good for

  • cache items and store sessions with expiration from an AI agent
  • store a conversation in a Redis stream
  • index and search vectors in Redis
  • manage event streams with consumer groups

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client connects and lists its tools

  • Replayed from scratch
  • Works offline
  • Checked on 15 Nov 2026
  • Version 0.5.1

An MCP client handshake over stdio listed 53 tools.

Differences the test machine hit

  • README: Connect to a Redis server at redis://localhost:6379/0
    In the test: The box has no Redis server and no root; the PyPI redis-server wheel is macOS-only, so a fakeredis TcpFakeServer (installed in a separate venv) stood in on port 6379 for the tool calls
  • README: query engine tools to manage vector indexes and perform vector search
    In the test: A Redis with the Query Engine (Redis 8 / Redis Stack). fakeredis has no FT.* commands, so get_indexes returned 'unknown command ft._list'
  • README: Python 3.14+ (uv python install 3.14)
    In the test: uv tool install redis-mcp-server installed and ran fine without a separate Python 3.14 step

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.