Overview
Connect AI assistants to the Onepostly API with the Model Context Protocol.
Connect AI assistants to the full Onepostly API using the Model Context Protocol (MCP). List accounts, publish, schedule, read analytics, and delete content across every supported platform, all through natural language.
The Onepostly MCP server exposes 7 tools covering the entire publishing lifecycle. It works with Claude, Claude Code, Cursor, and any MCP-compatible client.
Use Onepostly in your AI client
The server runs at https://mcp.onepostly.com. Approve access in the browser the first time your client connects. No API key required.
Claude.ai (web) go to Settings → Connectors → Add custom connector and enter
https://mcp.onepostly.comClaude Code one command
claude mcp add --transport http onepostly https://mcp.onepostly.comCursor / Claude Desktop add to mcp.json
{
"mcpServers": {
"onepostly": {
"url": "https://mcp.onepostly.com"
}
}
}Full steps for every client in Setup.
Setup
Client configuration, OAuth approval, and troubleshooting
Tools
All 7 tools with the full parameter reference and examples
What you can do
Ask your AI assistant things like
- "Post 'Hello world!' to X"
- "Schedule a LinkedIn post for tomorrow at 9am"
- "Show my connected accounts"
- "Cross-post this to X and LinkedIn"
- "How did my last Instagram post perform?"
- "Delete the tweet from last week"
- "What Pinterest boards do I have?"
- "Check my TikTok creator settings"
Example conversations
Publish a post
You Post "Just launched our new feature" to X
Assistant Published to X. Post ID
post_abc123
Schedule a post
You Schedule a LinkedIn post for tomorrow at 9am
Assistant Scheduled for tomorrow at 9am. Post ID
post_xyz789
Cross-post
You Post "Big news coming soon" to X and LinkedIn
Assistant Published to X and LinkedIn. Post ID
post_multi456