Model Context Protocol

Social Media MCP Server for AI Agents

Connect Claude, ChatGPT, Cursor, Claude Code or Codex to your workspace. Ask in plain words, and the assistant publishes and schedules your videos on 8 networks.

Start Free MCP Docs

Server URL: https://api.multi-upload-tool.com/mcp (Streamable HTTP, OAuth 2.1). Paste it as a connector in your AI client, sign in, and choose read-only or read + publish access. Posts go out through each network's official API, the same way as from the dashboard.

What the assistant can do

Publish & schedule

create_post to TikTok, YouTube, Instagram, Facebook, LinkedIn, Bluesky, Pinterest and Threads in one call, with a per-network caption.

Check before posting

validate_post dry-runs the post against every account's limits and required settings, without publishing.

Files from your phone

create_media_upload gives you a one-time link to drop a video, for chat apps that cannot send files.

Status, retries, analytics

get_post_status, retry_post, reschedule_post and get_analytics with the best hours to post.

Install it in your AI client

Claude (web, desktop, mobile)

Every plan, including Free (one custom connector). You sign in on a consent screen; no API key to copy.

Open Customize → Connectors → + → Add custom connector.
Paste https://api.multi-upload-tool.com/mcp and click Add.
Click Connect, pick your workspace and the access (read-only or read + publish), then approve.

ChatGPT

Web app, on Plus, Pro, Business, Enterprise and Edu.

Turn on Settings → Security and login → Developer mode.
In Plugins, click +, paste https://api.multi-upload-tool.com/mcp and choose OAuth.
Approve the consent screen on Multi Upload Tool.

Claude Code

Remote server with OAuth. With a shell, Claude Code can also presign and upload large files itself.

Run the command below, then type /mcp and choose Authenticate.

claude mcp add --transport http multi-upload https://api.multi-upload-tool.com/mcp

Cursor, Windsurf, Claude Desktop

Use the local bridge: it reads videos straight off your disk (up to 5 GB) and signs you in through your browser on first use. Requires Node 20+.

Add this to your MCP config (Cursor: ~/.cursor/mcp.json), then restart the app.

{
  "mcpServers": {
    "multi-upload-local": {
      "command": "npx",
      "args": ["-y", "multi-upload-tool-mcp"]
    }
  }
}

Codex CLI

Same local bridge, in Codex's TOML config. Requires Node 20+.

Add this to ~/.codex/config.toml.

[mcp_servers.multi-upload-local]
command = "npx"
args = ["-y", "multi-upload-tool-mcp"]

Every tool, scope and limit is in the MCP documentation.

Frequently Asked Questions

What is the Multi Upload Tool MCP server?

A Model Context Protocol server at https://api.multi-upload-tool.com/mcp. It lets an AI assistant such as Claude, ChatGPT, Cursor or Codex list your connected social accounts, publish or schedule video and image posts, check their status and read their analytics.

Do I need an API key?

No. The remote server uses OAuth: your AI client sends you to a consent screen on Multi Upload Tool, where you pick the workspace and whether the assistant can only read or also publish. You can revoke it at any time under API → Connected apps.

Can the assistant post a video that is on my computer or phone?

Yes. In Claude or ChatGPT, the assistant gives you a one-time link where you drop the file. In Cursor, Codex or Claude Desktop, the local bridge (npx -y multi-upload-tool-mcp) reads the file straight off your disk.

Is it free?

The MCP server is included in every plan, including the free plan (2 accounts, 13 uploads per month, no credit card).

Let your assistant post for you

Create a free account, connect your social accounts, then add the MCP server to your AI client.

Start Free