mcpField
U
UGC API

UGC API

Remote
ugcapi.devSocial Media0Updated 6d ago

About UGC API

UGC API is a remote MCP server for publishing and scheduling user-generated content to TikTok and Instagram. It supports individual posts and multi-account campaigns, with tools for tracking results and handling failures.

Key features

  1. 01Publish or schedule video and image posts
  2. 02Plan campaigns across multiple accounts
  3. 03Preview schedules and credit use
  4. 04Track post results and errors
  5. 05Manage connected creator accounts

Use cases

  1. 01Schedule a batch of videos across social accounts
  2. 02Publish a video as an Instagram Reel and Story
  3. 03Review failed posts and retry eligible ones

MCP support

Exposes UGC API publishing, scheduling, account, campaign, and statistics operations to MCP clients through a remote Streamable HTTP endpoint. Authentication uses OAuth 2.1.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://ugcapi.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

UGC API logo

UGC API MCP server

Remote MCP server for UGC API: publish and schedule user-generated content to TikTok and Instagram from Claude, ChatGPT, Cursor and any MCP client.

https://ugcapi.dev/mcp

Streamable HTTP with OAuth 2.1 (dynamic client registration, PKCE). There is nothing to install or host: add the URL as a remote MCP server, sign in with your UGC API email (a one-time code; new accounts get 50 free posts) and approve access to the workspace you have open.

Website · MCP docs · Claude plugin · Agent skill · n8n node · All integrations

What you can ask

  • "Which accounts do I have connected, and how many credits are left?"
  • "Post this video to my TikTok and as an Instagram Reel and Story: https://…/clip.mp4"
  • "Schedule these 20 videos across my 3 TikTok accounts, 2 a day at 10:00 and 18:00 New York time, starting Monday. Show me the plan first."
  • "What failed this week and why? Retry what can be retried."
  • "Create a link so a new creator can connect their Instagram account."

Tools

ToolWhat it does
get_account_overviewCredits, connected accounts and recent activity
list_accountsConnected TikTok and Instagram accounts
get_creator_infoTikTok nickname, privacy options and limits before posting
create_connect_linkA link a creator opens to connect their own account (no passwords shared)
upload_media_from_urlImport a public video or image
publish_postPost now or schedule to one or many accounts
preview_campaign / create_campaignPlan many posts across accounts on a cadence, preview schedule and credits first
list_posts / get_postResults per account and placement, public URLs and error reasons
cancel_post / retry_postCancel scheduled posts, retry failed ones
list_campaigns / cancel_campaignManage campaigns
get_statsViews, likes, comments and shares

Read-only tools are annotated as such; cancel tools are marked destructive. Posting publishes to real social accounts and uses credits ($10 per 1,000 posts). Facebook Pages and YouTube aren't available yet.

Setup by client

  • Claude: Settings → Connectors → Add custom connector → https://ugcapi.dev/mcp, or install the plugin.
  • Claude Code: claude mcp add --transport http ugcapi https://ugcapi.dev/mcp
  • Cursor / VS Code / others: add a remote server with URL https://ugcapi.dev/mcp; the client opens the sign-in page.

Prefer plain HTTP? The same features are in the REST API with an API key.

Links

Privacy · Terms · Support: [email protected]

This repository holds the public listing (server.json for the official MCP Registry); the server itself is hosted by UGC API. MIT license.

Comments

Markdown supported

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.