About kadenzo-mcp
kadenzo-mcp exposes Kadenzo’s social publishing and analytics API to MCP-capable agents. It supports scheduling and managing posts across 11 networks, along with listening and DM automation tools.
Key features
- 01Schedule posts across 11 networks
- 02Edit, cancel, and inspect posts
- 03Generate platform-specific post copy
- 04View account and post analytics
- 05Track mentions and keywords
- 06Manage DM automation rules
Use cases
- 01Schedule a post for future publication
- 02Review engagement across social accounts
- 03Track mentions of selected keywords
- 04Create or adjust DM automation rules
MCP support
It wraps the Kadenzo Studio public API as MCP tools for agents. Clients can use those tools to schedule, manage, and analyze social content.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y kadenzo-mcpKADENZO_API_KEYSecretKadenzo API key from studio.kadenzo.app/dashboard/settings?section=apiLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
13Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEKadenzo 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) |
list_keywords | List the social-listening keywords you track |
add_keyword | Track a new listening keyword (per-plan caps apply) |
update_keyword | Edit a keyword, or pause/resume it with is_active |
delete_keyword | Stop tracking a keyword |
get_listening_analytics | Mention volume, platform split, sentiment over time |
get_share_of_voice | Brand vs competitor Share of Voice report (Enterprise) |
list_dm_automations | DM automation rules + funnel stats + contact usage |
create_dm_automation | Create a DM automation rule (comment→DM, keyword DM, DM links, …) |
update_dm_automation | Edit a rule, or pause/resume it with active |
delete_dm_automation | Delete a DM automation rule |
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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.