kadenzo-mcp
Schedule, manage, generate, and analyze social posts across 11 networks (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Pinterest, Threads, Bluesky, Mastodon, Telegram) from any AI agent — 13 tools covering scheduling, media upload, AI caption generation, best-times, analytics, listening, and comments.
README
Kadenzo MCP server
Connect any MCP-capable AI agent — Claude Desktop, Cursor, ChatGPT, Codex — to Kadenzo and let it schedule, manage, and analyze social posts across 11 networks (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Pinterest, Threads, Bluesky, Mastodon, Telegram). It wraps the Kadenzo Studio public API as Model Context Protocol tools, so your agent doesn't just draft content — it can ship it.
Tools
| Tool | What it does |
|---|---|
list_accounts |
List connected accounts (ids + platforms) |
schedule_post |
Schedule a post for a future time (+ validate_only, options, thread) |
list_posts |
List your posts, newest first (filter by status, paginate) |
get_post |
One post: status, per-channel outcome, options/thread |
update_post |
Edit a not-yet-published post |
cancel_post |
Cancel a scheduled post before it publishes |
upload_media |
Upload a local image/video file, get a URL for media_urls |
get_account_analytics |
Recent posts + engagement metrics for an account |
get_post_analytics |
Per-channel metrics for a post you scheduled |
generate_content |
Generate post copy for a platform from a topic ("generate then schedule") |
get_best_times |
Personalized best posting times for an account (Professional+) |
list_mentions |
Social-listening mentions (who's talking about your keywords) |
post_comment |
Post a comment/reply to your post (instagram/facebook/linkedin) |
Setup
- Generate an API key in Kadenzo: Settings → API keys (
studio.kadenzo.app/dashboard/settings?section=api). The API is available on paid plans. - Add the server to your MCP client. Claude Desktop (
claude_desktop_config.json) / Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"kadenzo": {
"command": "npx",
"args": ["-y", "kadenzo-mcp"],
"env": { "KADENZO_API_KEY": "kdz_live_xxxxxxxxxxxxxxxxxxxxxxxx" }
}
}
}
- Restart the client. Ask your agent things like "list my connected accounts," "schedule this to X and Bluesky tomorrow at 9am," or "how did my last Instagram posts perform?"
Notes
- Posts are schedule-only — provide a future
scheduled_for; they publish automatically. KADENZO_API_BASEoverrides the API base URL (defaulthttps://studio.kadenzo.app/api/v1).- Requires Node 18+ (uses the built-in
fetch/FormData). - Learn more / full API reference: https://studio.kadenzo.app/developers · https://kadenzo.app
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.