INDIVIDUAL MCP TOOL

run_command

Run a shell command in the sandbox and get {stdout, stderr, exit_code}.

pilldrops.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://pilldrops.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for run_command and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.pilldrops]
url = "https://pilldrops.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "pilldrops": {
      "type": "http",
      "url": "https://pilldrops.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: pilldrops
Remote MCP URL: https://pilldrops.com/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": {
    "pilldrops": {
      "url": "https://pilldrops.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "pilldrops": {
      "type": "http",
      "url": "https://pilldrops.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "pilldrops",
  "transport": "streamable-http",
  "url": "https://pilldrops.com/mcp"
}

MCP Inspector

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

list_templates — List available sandbox templates (python-3.11, node, playwright, …) with their default resources.
create_sandbox — Create an isolated cloud sandbox.
list_sandboxes — List active sandboxes: id, template, status.
get_sandbox — Inspect one sandbox: status, resources, preview url when it serves an app.
start_server — Register + launch a persistent server command in the sandbox (survives idle-pause/resume, unlike run_command).
write_file — Write text content to a file in the sandbox workspace (path is relative to the workspace root; parent dirs are created).
read_file — Read a file from the sandbox workspace and return its content as text.
get_logs — Fetch recent sandbox logs (start command + service output) — the first stop when an app misbehaves or a preview 502s.