MCP Process MCP Server

An MCP server (Model-Client-Protocol) allowing Claude to access a shell. This integration enables Claude to execute commands and interact with your

Local serverstdioPython

What is the MCP Process MCP server?

An MCP server (Model-Client-Protocol) allowing Claude to access a shell. This integration enables Claude to execute commands and interact with your file system via the command line. The mcp process mcp server wraps that behind the Model Context Protocol, so an assistant can use it rather than through you.

What it actually does

  • Execution of static commands
  • Validation of potentially dangerous commands
  • Flexible configuration of command filtering and timeout

Configuration

  • Python 3.10 or higher (Python 3.11+ recommended) - WSL installed and configured - On Windows, the pywinpty package is required - On Linux/Mac, the ptyprocess package is required

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

When to reach for it

Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by jrame; 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.

Caveats

  • 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.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp process mcp server does with a few real requests.

How to install the MCP Process MCP server

Add the following section:

```json
"mcpServers": {
  "wsl": {
    "command": "mcp-process",
    "args": [
      "--process-path-args", "wsl.exe --cd /mnt/c/Users/YourName",
      "--filter-patterns", "\\x1b\\[[0-9;]*m",
      "--exec-name", "exec",
      "--exec-description", "Exécute une commande statique (ls pwd cat tree ps mkdir cp grep find git sed echo rg ...) et retourne son résultat",
      "--exec-timeout", "60"
    ]
  },
  "psql": {
    "command": "mcp-process",
    "args": [
      "--process-path-args", "psql.exe postgresql://postgres:password@localhost:5432/db",
      "--exec-name", "psql",
      "--exec-description", "Exécute une commande statique sql et retourne son résultat ex: -c \"SELECT * FROM table;\" ",
      "--exec-timeout", "120"
    ]
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.10 or higher (Python 3.11+ recommended) - WSL installed and configured - On Windows, the pywinpty package is required - On Linux/Mac, the ptyprocess package is required

Frequently asked questions

It connects MCP Process to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with MCP Process directly.