Skip to Content
MCP ServerOverview

MCP Server

The QiQ Social MCP (Model Context Protocol) server lets AI assistants like Claude manage your social media automations, create and publish posts, and interact with your workspace — all through natural language.

What is MCP?

Model Context Protocol  is an open standard that allows AI assistants to securely connect to external tools and data sources. With the QiQ Social MCP server, you can control your entire content pipeline from Claude Desktop, Claude Code, VS Code, or any MCP-compatible client.

Available Tools

ToolDescription
list_workspacesList all workspaces you have access to
list_automationsList automations in a workspace
get_automationGet details of a specific automation
create_automationCreate a new automation with scheduling and channel targeting
update_automationUpdate automation settings
delete_automationDelete an automation
run_automationTrigger content generation immediately
list_connectionsList platform OAuth connections
list_channelsList publishing channels (Facebook pages, Telegram groups, etc.)
list_postsList posts with status and automation filters
get_postGet post details including content and metrics
create_postCreate a draft post for a channel
update_postEdit a draft post’s content
delete_postDelete a draft post
publish_postPublish a post to its platform
list_sourcesList RSS feed sources
create_sourceAdd an RSS feed source
delete_sourceRemove an RSS feed source
validate_rssValidate an RSS feed URL
text_assistAI text enhancement (proofread, rephrase, generate)
media_assistSearch stock photos or generate AI images
generate_hashtagsGenerate platform-optimized hashtags
list_assetsList media library assets
list_labelsList workspace labels
get_subscription_statusCheck plan and usage limits

Installation

No API keys or configuration needed — the server connects to QiQ Social automatically.

Claude Desktop

Edit your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{ "mcpServers": { "qiq-social": { "command": "npx", "args": ["-y", "@qiq/mcp"] } } }

Claude Code

claude mcp add qiq-social -- npx -y @qiq/mcp

VS Code

Add to .vscode/mcp.json:

{ "servers": { "qiq-social": { "command": "npx", "args": ["-y", "@qiq/mcp"] } } }

Remote (HTTP)

If you prefer not to install anything locally, you can connect to the hosted MCP server at mcp.qiq.social.

Claude Desktop — edit your config file:

{ "mcpServers": { "qiq-social": { "type": "url", "url": "https://mcp.qiq.social/mcp" } } }

VS Code — add to .vscode/mcp.json:

{ "servers": { "qiq-social": { "type": "http", "url": "https://mcp.qiq.social/mcp" } } }

How It Works

The MCP server supports two transport modes:

  • Local (stdio): Runs on your machine via npx. Your AI assistant spawns and communicates with the process directly.
  • Remote (HTTP): Hosted at mcp.qiq.social. Your AI client connects over HTTP using the Streamable HTTP transport.

Both modes connect to the same QiQ Social backend with built-in credentials — no API keys needed.

AI Assistant ←→ MCP Server (local or remote) ←→ QiQ Social API
  1. Your AI assistant connects to the MCP server (spawns locally or connects via HTTP)
  2. The server connects to QiQ Social using the built-in API credentials
  3. Tools execute queries and operations on your behalf
  4. Results are returned to the assistant as structured data

Automation Types

When creating automations, use these types:

TypeDescriptionRequires Topic
write_socialAI-generated social media postsYes
write_blogAI-generated blog articlesYes
rss_socialRepurpose RSS feed items as social postsNo
rss_blogRepurpose RSS feed items as blog articlesNo
rss_digest_blogDigest multiple RSS items into one blog postNo

Post Content Structure

Social Posts

{ "content": "Your post text here", "media": [ { "type": "image", "url": "https://example.com/photo.jpg" } ] }

Blog Posts (WordPress, Webflow)

{ "title": "Article Title", "content": "<h2>Heading</h2><p>HTML content...</p>", "excerpt": "A short summary", "tags": ["marketing", "ai"], "media": [ { "type": "image", "url": "https://example.com/hero.jpg" } ] }

Discord Posts (with embed)

{ "content": "Check out this article!", "embed": { "title": "Article Title", "description": "Article summary", "url": "https://example.com/article" } }

Platform Constraints

Each channel placement has character limits and media constraints:

PlatformPlacementMax CharactersMax Media
Instagraminstagram_account2,20010
Facebookfacebook_page63,20680
LinkedInlinkedin_profile3,00020
Xx_profile2804
Telegramtelegram_channel4,09610
Discorddiscord_channel2,000
Threadsthreads_profile50010
Pinterestpinterest_board5001
Blueskybluesky_profile3004
Last updated on