New:Introducing Socket Scanning for VS Code Marketplace Extensions.Learn more →
Get Started

@postquickai/mcp

Package Overview
Dependencies
Maintainers
1
Versions
6
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@postquickai/mcp

MCP server for PostQuickAI — schedule posts, generate content, and manage social media accounts from Claude Code, Cursor, Codex, ChatGPT, OpenClaw, and any MCP-compatible agent.

latest
npmnpm
Version
0.1.5
Version published
Weekly downloads
0
Maintainers
1
Weekly downloads
 
Created
Source

@postquickai/mcp

Official MCP server for PostQuickAI — schedule social media posts, generate AI content (images, videos, captions, threads), manage connected platforms, and pull analytics from any MCP-compatible agent.

40+ tools, auto-generated from the live PostQuickAI v1 API, so the tool list always stays in sync.

Works with:

  • Claude Code & Claude Desktop
  • OpenAI Codex CLI
  • Cursor (global or project-scoped)
  • ChatGPT Desktop (Experimental → MCP)
  • Google Gemini CLI
  • GitHub Copilot (VS Code agent mode)
  • OpenClaw (formerly Clawdbot)
  • Continue.dev, Aider, OpenHands
  • Any other MCP-compatible client

Install

claude mcp add postquickai \
  -e POSTQUICKAI_API_KEY=pq_live_your_key_here \
  -- npx -y @postquickai/mcp

# Verify
claude mcp list

The -- separator is required — everything after it is the command and its args. Without it, Claude Code treats the whole string as the binary name and fails to connect.

Claude Desktop

Edit claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

(Or from inside Claude Desktop: Settings → Developer → Edit Config.)

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

Fully quit (Cmd+Q / tray → Quit) and reopen.

Cursor

  • UI: Settings (Cmd+, / Ctrl+,) → Features → MCP → + Add New MCP Server
  • Config file: .cursor/mcp.json (project) or ~/.cursor/mcp.json (global)

Same JSON shape as Claude Desktop.

OpenAI Codex CLI

codex mcp add postquickai -- npx -y @postquickai/mcp

Then add your API key to ~/.codex/config.toml:

[mcp_servers.postquickai]
command = "npx"
args = ["-y", "@postquickai/mcp"]
env = { POSTQUICKAI_API_KEY = "pq_live_your_key_here" }

Google Gemini CLI

Edit ~/.gemini/settings.json (global) or .gemini/settings.json (project):

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

Gemini expands $POSTQUICKAI_API_KEY from your shell environment at runtime.

GitHub Copilot (VS Code agent mode)

Create .vscode/mcp.json at your repo root:

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

Open Copilot Chat → switch to Agent mode.

ChatGPT Desktop

Settings → Experimental → Model Context Protocol → paste the Claude Desktop JSON above → fully restart.

OpenClaw

Add to your character file's mcpServers block (same JSON shape as above) and restart the agent.

Get an API key

Keys start with pq_live_. Keep them secret — never commit them. Use environment-variable expansion ($POSTQUICKAI_API_KEY / ${env:POSTQUICKAI_API_KEY}) where your client supports it.

Capabilities

Auto-generated from the live OpenAPI spec at https://www.postquick.ai/openapi.json:

  • Content groups — listContentGroups, createContentGroup, deleteContentGroup, getInstructions, updateInstructions, getGroupAnalytics
  • Posts — listPosts, createPost, generatePost, getPost, updatePost, publishPost, schedulePost, regeneratePost, resetPostPlatforms, deletePost, getPostAnalytics
  • Threads — reply-based threads for Twitter/X, Threads, Bluesky
  • Images — generateImage (Gemini Flash, GPT Image 1.5, Nano Banana Pro)
  • Videos — generateVideo, getVideoStatus, publishVideo, scheduleVideo, resetVideoPlatforms, updateVideo, deleteVideo
  • Content tools — generateCaption, generateCarouselCaption, generateVideoCaption, generateHashtags, adjustTone, proofread, makeConcise, customEdit
  • Accounts — listAccounts, disconnectAccount
  • Usage — getMe, getUsage

Pair with Skills

For opinionated workflows on top of raw tools, install the companion kodenark/postquickai-agent-skills marketplace:

  • schedule-post — single-post scheduling
  • weekly-content-batch — plan + generate + schedule a week of content
  • analyze-post-performance — deep analytics summary
  • onboard-brand — full brand setup in one guided flow
  • reply-thread — multi-platform thread creation
  • daily-digest — end-of-day publishing summary

Claude Code: /plugin marketplace add kodenark/postquickai-agent-skills Codex: codex plugin install kodenark/postquickai-agent-skills

AGENTS.md drop-in

Teach any agent that reads AGENTS.md (Codex, Copilot, Cursor, Claude Code, Continue, Aider, OpenHands) how to use PostQuickAI by pasting the snippet from https://www.postquick.ai/agents-md into your repo root.

Troubleshooting

"Failed to connect to postquickai"

Almost always a config-format issue:

  • command must be just npx (not the whole string)
  • args must be an array (["-y", "@postquickai/mcp"])
  • For Claude Code: you forgot the -- separator
  • Fully quit and restart your agent after editing config

"API add-on required" / 403

API access is included on every current plan. If you see this, your account is on a legacy plan without the API add-on: switch to a current plan at postquick.ai/pricing.

"Missing POSTQUICKAI_API_KEY"

The MCP server needs the key in its env block (or expanded from a shell var). Generate one at postquick.ai/dashboard/api. Keys start with pq_live_.

Rate limits

  • Basic plan: 30 req/min, 5k/day
  • Pro plan: 120 req/min, 50k/day

See rate limits docs.

License

MIT

Keywords

mcp

FAQs

Package last updated on 18 Oct 2026

Related posts