← Registry

Developer Tools

nl2shell.com

Translates natural language to shell commands, executes them in a sandbox, and explains commands.

1 endpoint3 known toolsFirst detected May 10, 2026Last detected August 20, 2026

ENDPOINT 1

https://nl2shell.com/api/mcp

No auth detected

MCP server metadata

Name
leshell
Version
1.0.0
Capabilities
tools

Known tools 3

leshell_translate

Translate a natural language description into a shell command.

Potential side effects
leshell_execute

Execute a shell command inside an isolated Docker sandbox container.

Potential side effects
leshell_explain

Explain what a shell command does in plain English.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.leshell]
url = "https://nl2shell.com/api/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "leshell": {
      "type": "http",
      "url": "https://nl2shell.com/api/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: leshell
Remote MCP URL: https://nl2shell.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "leshell": {
      "url": "https://nl2shell.com/api/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "leshell": {
      "type": "http",
      "url": "https://nl2shell.com/api/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "leshell",
  "transport": "streamable-http",
  "url": "https://nl2shell.com/api/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for nl2shell.com was fetched 2026-07-28T03:30:34.792Z and is being refreshed.

Trust status Neutral

nl2shell.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.