mcp

Run the adscapi MCP server over stdio. Point any MCP client at it and an agent gets four tools: platforms, check, verify, track. Platform tokens come from the server process environment.

Usage

shell

adscapi mcp

No flags. The process stays up and speaks MCP on stdin/stdout — you almost never run this by hand; the MCP client launches it.

Wire it into a client

Claude Code:

shell

claude mcp add adscapi -- npx -y adscapi mcp

Cursor, Codex CLI, Gemini CLI, opencode:

jsonc

// .mcp.json
{
  "mcpServers": {
    "adscapi": {
      "command": "npx",
      "args": ["-y", "adscapi", "mcp"]
    }
  }
}

Tools

Tool	Use it to
`adscapi_platforms`	List every destination, support level, and required secrets
`adscapi_check`	See which platforms are configured right now
`adscapi_verify`	Live-check that a configured token actually works
`adscapi_track`	Fire one canonical conversion to every configured platform

Environment

The server reads tokens from its own process environment — export them in the shell that launches the client, or set env in the MCP config. Same secret names as adscapi platforms.

mcp

Usage

Wire it into a client

Tools

Environment

Related