Prodex MCP Server

Local receipt bus for coordinating Codex execution with ChatGPT Pro/Projects consultation.

Local serverstdioGo

What is the Prodex MCP server?

Local receipt bus for coordinating Codex execution with ChatGPT Pro/Projects consultation. That is what the prodex mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 5 tools. What each one is for:

  • Manual-first — each ChatGPT Pro consult should be user-initiated or clearly tied to the current task
  • Read — only result artifact fetch for Pro consult and generic MCP handoff artifacts explicitly listed on result records
  • Claude — compatible stdio MCP server through prodex mcp
  • Receipt — gated repo write/stage tools for existing text files: dry-run first, apply only with matching git HEAD and preimage hash, then stage only reviewed
  • login — -dry-run prints the dedicated Chrome profile, debug URL, and next commands without opening a browser

Getting it running

Installation goes through your MCP client rather than a global install: point it at @youdie006/prodex on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Plenty of developer tooling 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. Prodex's toolset — Manual-first, Read, Claude and 2 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; 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.

Things to watch

  • 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.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Manual-firsteach ChatGPT Pro consult should be user-initiated or clearly tied to the current task.
Readonly result artifact fetch for Pro consult and generic MCP handoff artifacts explicitly listed on result records.
Claudecompatible stdio MCP server through prodex mcp.
Receiptgated repo write/stage tools for existing text files: dry-run first, apply only with matching git HEAD and preimage hash, then stage only reviewed applied receipts.
login-dry-run prints the dedicated Chrome profile, debug URL, and next commands without opening a browser.

How to install the Prodex MCP server

{
  "mcpServers": {
    "prodex": {
      "command": "npx",
      "args": ["-y", "@youdie006/prodex"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Prodex to Manual-first.
  • Use Prodex to Read.
  • Use Prodex to Claude.

Frequently asked questions

It connects Prodex to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (Manual-first, Read, Claude, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Prodex directly.