Awaberry MCP Server

A Node.js based Model Context Protocol (MCP) server to remote connect to devices without the need for SSH, VPN and open ports to manage files

Local serverstdio

What is the Awaberry MCP server?

Awaberry MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A Node.js based Model Context Protocol (MCP) server to remote connect to devices without the need for SSH, VPN and open ports to manage files, connect to databases and execute terminal commands in a persistent long running terminal session.

What the assistant can call

Once Awaberry is connected, these are the calls the assistant has available:

  • Parameters — **
  • Returns — **
  • Tools — Connects to a remote device (Mac, Linux, Windows, or Docker) registered in your awaberry project
  • Prerequisites — The Prerequisites tool exposed by this server
  • Download — Open a terminal and optionally create a folder for the awaBerry mcp server

Configuration and credentials

You will need 2 environment variables: AWABERRY_PROJECT_KEY, AWABERRY_PROJECT_SECRET. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

PWD on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Awaberry's toolset — Parameters, Returns, Tools and 2 more — is a fair guide to whether it matches your workflow. It is maintained by awaberry; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the awaberry mcp server does with a few real requests.

Available tools

ToolWhat it does
Parameters**
Returns**
ToolsConnects to a remote device (Mac, Linux, Windows, or Docker) registered in your awaberry project.
PrerequisitesThe Prerequisites tool exposed by this server.
DownloadOpen a terminal and optionally create a folder for the awaBerry mcp server

How to install the Awaberry MCP server

{
  "mcpServers": {
    "server-awaberry": {
      "command": "npx",
      "args": ["-y", "PWD"],
      "env": {
        "AWABERRY_PROJECT_KEY": "your-value",
        "AWABERRY_PROJECT_SECRET": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
AWABERRY_PROJECT_KEYCredential the server authenticates with.Yes
AWABERRY_PROJECT_SECRETCredential the server authenticates with.Yes

Example prompts to try

  • Use Awaberry to Parameters.
  • Use Awaberry to Returns.
  • Use Awaberry to Tools.

Frequently asked questions

It connects Awaberry to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (Parameters, Returns, Tools, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Awaberry directly.