Post to X from n8n: coming soon

Can n8n post, reply or send direct messages on X through Postgale?

Coming soon: X is not available yet. An X account cannot be connected in Postgale today, so nothing on this page works against X yet. What is planned may change before launch.

Postgale is the secure layer for AI agents on social media. MCP (Model Context Protocol) is the open standard that lets AI assistants such as Claude and Cursor use outside tools. An MCP server is what they connect to. Until X is live, Dashboard → Accounts shows X as “Coming soon”, and an n8n AI agent gets no X account to act on.

What is planned for X?

The plan is the official X API v2, with the same approval, audit log and revocable access as the other platforms. Details may change before launch:

• Posts, threads, polls and quote posts with images, a GIF or a video.
• Replies, mentions and direct messages.
• Recent search and post metrics.
• X’s own rules applied before anything is sent, such as its 280 weighted-character limit.

Set up n8n with Postgale today

How do I set up the MCP Client Tool node?

1. In Postgale, open Dashboard → API keys, create a key and copy it (it starts with sk_ and is shown once). Connect the social accounts the agent may use under Dashboard → Accounts.
2. Add an AI Agent node with your model, and attach an MCP Client Tool node to it.
3. In the MCP Client Tool node set the endpoint to https://postgale.com/mcp, the transport to HTTP streamable, and authentication to a Bearer or Header Auth credential carrying Authorization: Bearer sk_….
4. Leave the tool list on “all” to start, or select only the read-only tools until you trust the workflow.
5. Give the agent a system prompt that states the account ids it may use and whether it must save drafts or may schedule.

Ask your agent“You manage the Northline accounts in Postgale (ids in the context). For each new blog post in the input, draft one Instagram caption with the cover image and one Threads post, save them as drafts, and reply with the Postgale post ids.”

How do I set up the HTTP Request node?

1. In Postgale, open Dashboard → API keys, create a key and copy it (it starts with sk_ and is shown once). Connect the social accounts the agent may use under Dashboard → Accounts.
2. In n8n create a credential of type Header Auth with name Authorization and value Bearer sk_… (your key).
3. Add an HTTP Request node: method POST, URL https://postgale.com/api/v1/posts, authentication Header Auth with that credential, body type JSON:

{
  "content": "{{ $json.caption }}",
  "scheduledFor": "{{ $json.publishAt }}",
  "platforms": [
    {
      "accountId": "acc_instagram",
      "platformSpecificData": {
        "mediaUrl": "{{ $json.imageUrl }}"
      }
    },
    {
      "accountId": "acc_threads"
    }
  ]
}

1. Get the account ids once with a GET to https://postgale.com/api/v1/accounts using the same credential.
2. Optional: send an x-request-id header built from your trigger id, so a re-run of the workflow returns the same post instead of a duplicate.
3. To know when the post is live, add a Webhook node and register its URL in Postgale (Dashboard → Webhooks); Postgale sends post.published or post.failed, signed with HMAC-SHA256.

What can the agent do through Postgale today?

An agent can publish today on Instagram, Facebook Pages, Threads, TikTok, Telegram, Discord, Bluesky and Mastodon, and answer customers on WhatsApp Business. X is coming soon.

Nothing has to go out unreviewed. Approval can be required per workspace, per connected account, per API key or per signed-in app; while it applies, posts wait as pending approval in the dashboard, and replies, direct messages and edits to live posts are refused. Every write the agent makes is kept in the audit log.

Common questions