threads-post

Files (1)

• SKILL.md

SKILL.md (first lines)

# Threads Post

Create and schedule posts on Meta's Threads using the Publora MCP server. Supports single posts, multi-part chains (connected replies), image carousels (2-20 images) and reply control.

## Prerequisites

**Plans:** Works on the free Starter plan. Current limits and pricing: [publora.com/pricing](https://publora.com/pricing).

### Getting Started

1. **Create account** at [publora.com/register](https://publora.com/register) (free)
2. **Connect Threads** via Instagram OAuth in [Publora Dashboard](https://app.publora.com/dashboard)
3. **Get an API key** at [app.publora.com/dashboard/api](https://app.publora.com/dashboard/api), only if your agent cannot sign in with OAuth or you will use the REST API fallback below
4. **Connect your agent** to the MCP server at `https://mcp.publora.com/mcp`:
   - **Upgrading a manual connection without `/mcp`:** Claude treats `https://mcp.publora.com` as a different server from the bundled one. Change that existing connection to `https://mcp.publora.com/mcp` in its current scope, preserving its authentication and chosen account; sign in again if requested. Alternatively, verify the bundled connection uses the intended account, then remove only the old manual entry. Do not add a second entry or delete credentials automatically.
   - **Publora tools already available** (the `publora-skills` plugin or the Publora connector in Claude): nothing to set up. Claude asks you to sign in to Publora the first time a tool runs.
   - **Agents that support OAuth** (Claude Code, Cursor, and the Claude and ChatGPT apps): add the server by URL and sign in, no API key needed. In Claude Code, add it and then run `/mcp` to sign in:

```bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp
```

   - **Agents without OAuth:** send the API key as `Authorization: Bearer sk_YOUR_API_KEY`:

```bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp \
  --header "Authorization: Bearer sk_YOUR_API_KEY"
```

   Claude Desktop, Cursor, Codex, OpenClaw and the claude.ai connector each need a different config file or flow: see [client setup](https://docs.publora.com/mcp/client-setup) for the exact path and snippet.

### REST API Fallback

If MCP is unavailable, use the REST API directly:

**Base URL:** `https://api.publora.com/api/v1`

**Authentication:** `x-publora-key` header

```bash
# Get connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
  -H "x-publora-key: sk_your_api_key"

# Create a post
curl -X POST "https://api.publora.com/api/v1/create-post" \
  -H "x-publora-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "platforms": ["threads-12345"],
    "content": "Your post content",
    "scheduledTime": "2026-03-25T10:00:00Z"
  }'
```

**Platform ID Format:** `threads-{id}` (from `/platform-connections`)

📖 **Docs:** [docs.publora.com](https://docs.publora.com)

## Platform Limits

| Feature | Limit |
|---------|-------|
| Characters per post | 500 (per part in a chain) |
| Hashtags | 1 per post maximum |
| Links | 5 per post maximum |
| Images per carousel | 2-20 |
| Image size | 8 MB |
| Image formats | JPEG, PNG (WebP auto-converted) |
| Video duration | 5 minutes |
| Video size | 1 GB |
| Video formats | MP4, MOV |
| Posts per day | 250 |
| Replies per day | 1,000 |

## Available Tools

### create_post
Create a new Threads post or thread.

**Parameters:**
- `platforms`: Array with your Threads connection ID (e.g., `["threads-12345"]`)
- `content`: Post text (auto-threads if over 500 chars)
- `scheduledTime`: ISO 8601 UTC datetime. **Optional**: omit it and the post is created as a draft. Send a future time to schedule. A time five or more minutes in the past is rejected with `SCHEDULED_TIME_IN_PAST`, so for immediate posting use the current time plus a minute.
- `mediaUrls`: up to 10 public **https** image or video URLs. Publora downloads them server-side and attaches them *before* validation, so media and scheduling happen in one call. This is the one-shot alternative to the draft then `get_upload_url` then `complete_media` flow. Ingestion is rate-limited to 60 URLs per hour.

### get_upload_url
Get a presigned URL to upload images.

### complete_media
Finalize a file uploaded through `get_upload_url`, after the presigned `PUT` succeeds. Optional, because scheduling also finalizes pending media, but calling it early surfaces format and probe errors before publish. Not needed for media attached with `mediaUrls`.

**Parameters:**
- `mediaId`: the id returned by `get_upload_url`

### list_connections
List your connected accounts with their platform IDs. Call this first and copy the IDs verbatim; they are never guessable.

### list_posts / get_post / update_post / delete_post
Manage scheduled and draft posts. `update_post` also patches `content` and `platforms` on a draft or scheduled post, so fixing a typo or retargeting no longer means delete and recreate. `delete_media` and `prune_media_reference` clean up uploaded files.

## Multi-Part Chains

Put the whole text in one `content` field. Publora publishes it as a chain of connected replies, each part a reply to the previous one.

- **Automatic split:** content over 500 characters is split into a chain instead of being rejected. Splits prefer paragraph breaks, then line breaks, then sentence endings, then word boundaries. Automatically split parts get a ` (1/3)`-style suffix, and 10 of each part's 500 characters are reserved for it, so roughly 490 characters of your text land in each part. Emoji count as 2.
- **Your own breaks:** a line containing only `---` (with a newline before and after) sets a break. A complete set of `[1/3]`, `[2/3]`, `[3/3]` markers works too. Parts you separate yourself are published exactly as written, with no numbering added. An oversized `---` part is re-split automatically; an oversized `[n/m]` part is rejected with `THREAD_PART_TOO_LONG`.
- **Media:** attached to the first part only; later parts are text-only.
- **Permission:** a chain needs `threads_manage_replies` on the connection. Without it the post is rejected with `THREADS_PERMISSION_REQUIRED` **before any part is published**; reconnect the account in Publora Channels and approve every permission. Single posts and carousels don't need it.
- **Checking the result:** `get_post` returns `isThread: true` and one `threadParts[]` entry per part (`index`, `content`, `status`, `publishedId`). If a chain fails part-way (`THREAD_PARTIALLY_PUBLISHED`) or the outcome is unknown, the published parts are live: publish only the missing parts, never recreate the whole chain.

There is no `parts` array and no numbering or threading switch in MCP or REST: `content` is the only input.

## Reply Control

Control who can reply to your posts via REST API `platformSettings`:

| Value | Description |
|-------|-------------|

From publora/skills, MIT.

More from publora/skills