ChatGPT Integration

PostQuickAI for ChatGPT

Two integration paths — MCP in ChatGPT Desktop for the full toolkit, or a Custom GPT Action for the web and mobile. Either way, your social media scheduler lives inside the conversation you're already having.

Option A — ChatGPT Desktop (MCP)

In ChatGPT Desktop: Settings → Experimental → Model Context Protocol. Paste:

{
  "mcpServers": {
    "postquickai": {
      "command": "npx",
      "args": ["-y", "@postquickai/mcp"],
      "env": {
        "POSTQUICKAI_API_KEY": "pq_live_your_key_here"
      }
    }
  }
}

Fully restart ChatGPT Desktop. Verify by asking "list my PostQuickAI content groups" — if the tool fires, you're done.

Option B — Custom GPT Action (web + mobile)

  1. Go to chatgpt.com/gpts/editor and create a new GPT
  2. In the Configure tab, scroll to ActionsCreate new action
  3. Click Import from URL and paste:
https://www.postquick.ai/openapi.json

Set authentication:

Auth Type: API Key
Auth Type (detail): Bearer
API Key: pq_live_your_key_here

Save + publish. Now the GPT can call any of the 40 PostQuickAI endpoints. Share it with your team (each user supplies their own API key for production use).

Example prompts

"Show me my PostQuickAI usage for this month — am I close to the image limit?"
"Schedule three posts about our Q1 launch — one each for Twitter, LinkedIn, and Threads. Space them out across Tuesday-Thursday."
"Pull last 30 days of engagement and identify my top-performing content format"
"Create a 7-tweet thread unpacking our latest blog post and schedule it for Thursday 10am ET"

API + Agent access

MCP server, Skills, and REST API are all included with the API add-on on any paid plan.

FAQ

Frequently Asked Questions

ChatGPT Desktop supports MCP on macOS and Windows via the same claude_desktop_config-style mcpServers block. The web app and mobile apps don't run MCP locally — for those, use a Custom GPT with an Action.

Open ChatGPT Desktop → Settings → Experimental → Model Context Protocol. Paste the PostQuickAI server block, save, and fully restart ChatGPT Desktop.

Go to chatgpt.com/gpts/editor → Configure → Actions → "Import from URL" and paste https://www.postquick.ai/openapi.json. Set Auth to API Key, Header name `Authorization`, value `Bearer pq_live_your_key`.

MCP runs locally via stdio — works in ChatGPT Desktop, zero server cost. Custom GPT Actions call our REST API directly — works in ChatGPT web/mobile, visible to anyone you share the GPT with. Both use the same API key.

Yes, but each user needs their own PostQuickAI API key. Set auth to "API Key (per-user)" so each conversation prompts for the user's own key. Never hard-code your key into a public GPT.

No. Both paths hit the same PostQuickAI v1 API with the same limits. Basic: 30 req/min, 5k/day. Pro: 120 req/min, 50k/day.

Troubleshooting

"Failed to connect to postquickai"

Almost always a config format issue. Make sure command is just npx and args is an array — never put the whole command in one string. Also fully quit and restart your agent after editing config.

"API add-on required" / 403 errors

MCP and REST API access both require the API add-on on your plan. Enable it at postquick.ai/pricing.

"Missing POSTQUICKAI_API_KEY"

Generate a key at postquick.ai/dashboard/api. Keys start with pq_live_. Put it in the env block of your MCP config.

Rate limit exceeded

Basic plan: 30 req/min, 5k/day. Pro plan: 120 req/min, 50k/day. See rate limits in the API docs.

ChatGPT-specific issues

Still stuck? See the developer docs or email support@postquick.ai.

Also works with

PostQuickAI is agent-native — same API, same MCP server, same skills bundle across every major AI coding agent.

Turn ChatGPT into your content operations engine

One API key. Two integration paths. Every PostQuickAI tool available from plain English.

Start free trial