linkedin/post

What it does

Post to LinkedIn feed

Install Taprun once

Taprun ships as a single MCP server exposing a catalog of compiled taps. One-time setup on macOS / Linux:

brew install LeonTing1010/tap/taprun
tap mcp connect

Or drop this into your claude_desktop_config.json (works identically in Claude Code, Cursor, Cline, Windsurf — any MCP host):

{
  "mcpServers": {
    "tap": {
      "command": "tap",
      "args": ["mcp", "start"]
    }
  }
}

Call linkedin/post

Terminal, once installed:

tap run linkedin/post

From the MCP host — exact same compiled plan, deterministic replay, zero LLM tokens:

tap.run({ site: "linkedin", name: "post" })

Why compile it once

This plan was forged once — the AI read linkedin, picked stable structural addresses (JSON-LD, ARIA, RSS, or declared API endpoints, in that priority order), and saved them to a .plan.json. Every replay since then has used zero LLM tokens. When linkedin ships a site change that breaks the extraction, tap verify surfaces it before your data goes stale — not after your pipeline silently writes garbage for a week.