Antwork

io.antworkPublished by antwork.ioOfficial publisherv1.0.4Updated Nov 6, 2026

Draft, schedule, and publish social posts for your workspace straight from your AI.

VerifiedStreamable HTTPWeb executableCommunication & CollaborationBusiness & Commerce

Overview

AI-generated overview

Antwork is a remote MCP server that lets an AI assistant draft, schedule and publish social posts to connected accounts across LinkedIn, X, Instagram and more.

What you can do
  • Draft posts in each account's own voice, after reading that account's recent posts
  • Schedule or publish single posts or multi-account campaigns, and retry failed ones
  • Attach images, video and PDFs and manage the media library
  • View the calendar, list and search posts
  • Report per-post and per-account performance metrics and daily follower counts
  • Connect social accounts and get connect links per platform
When to use it
Useful when you want an assistant to handle social publishing end to end: turning releases or commits into posts, planning a content calendar, repurposing one piece across platforms, or pulling engagement reports and audits for connected accounts.
Requirements
A remote MCP endpoint at the Antwork server URL over Streamable HTTP; OAuth 2.1 sign-in with dynamic client registration (no API key to create). An MCP-capable client such as VS Code with GitHub Copilot, Claude, ChatGPT or Cursor. Connected social accounts; Instagram needs a Creator or Business account. Two accounts are free, then a monthly fee per account.
Before you install
The assistant can publish posts publicly to real social accounts, so drafts should be reviewed before scheduling or publishing. OAuth grants access to all your workspaces with a single token. Paid tier applies beyond two social accounts. Platform rules restrict media (Instagram and Pinterest need an image or video; TikTok and YouTube need video). Optional skills installs run shell scripts or copy files into local config directories.

Installation

In SourceWeft

  1. Open Antwork in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.antwork%2Fsocial/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "antwork": {
      "type": "http",
      "url": "https://api.antwork.io/mcp"
    }
  }
}

README

Antwork: post to LinkedIn, X, Instagram and more from your AI

[skills.sh]

AI assistants have no built-in connector for posting to social media. To let your assistant draft, schedule and publish posts, you connect it to an MCP server that holds the platform permissions. Antwork is that server: connect https://api.antwork.io/mcp once, sign in with OAuth, and your assistant can post to your connected accounts on LinkedIn (personal profile or company page), X, Instagram, Facebook Pages, Threads, TikTok, YouTube and Pinterest. Posts stay drafts until you ask it to schedule or publish them.

It works in VS Code (GitHub Copilot chat), Claude, ChatGPT, Cursor and any other client that speaks MCP. Two social accounts are free, then $5 a month each (pricing).

Install in one line

Pick your agent. Each line adds the Antwork skills (including /antwork ship, which turns your commits and releases into posts); the plugin lines also connect the MCP server.

AgentCommand
Claude Code (plugin: skills, audit agents and MCP server)/plugin marketplace add polynode-co/antwork then /plugin install antwork@antwork
Codex (plugin: skills and MCP server)codex plugin marketplace add polynode-co/antwork && codex plugin add antwork@antwork && codex mcp login antwork
Any agent, skills only (skills CLI: Claude Code, Codex, Cursor and others)npx skills add polynode-co/antwork

The skills CLI installs skills, not MCP servers, so connect the server once yourself:

sh
# Claude Codeclaude mcp add --transport http antwork https://api.antwork.io/mcp# Codexcodex mcp add antwork --url https://api.antwork.io/mcp && codex mcp login antwork

Or in Codex's ~/.codex/config.toml:

toml
[mcp_servers.antwork]url = "https://api.antwork.io/mcp"

Then, from inside a repo: /antwork ship (or just "post about what I shipped this week").

Connect

Server URLhttps://api.antwork.io/mcp
Server nameantwork
TransportStreamable HTTP
AuthOAuth 2.1 with dynamic client registration. No API key to create or store.

The first tool call opens a consent screen in your browser. After that, ask your assistant to connect a social account and it returns a connect link for each platform.

VS Code

Install Antwork from the MCP servers gallery, or add it in one click. MCP servers in VS Code run through GitHub Copilot, so the Copilot extension must be installed and signed in. To add it by hand, put this in .vscode/mcp.json:

json
{  "servers": {    "antwork": {      "type": "http",      "url": "https://api.antwork.io/mcp"    }  }}

Other clients

  • Claude.ai or Claude Desktop: add https://api.antwork.io/mcp as a custom connector. Step-by-step. For the calendar, campaign, analytics and audit workflows, add the claude.ai skill too.
  • Claude Code: install the plugin below, which connects the server and adds the skills in one step.
  • ChatGPT: setup guide.
  • Cursor, and Grok Bot through Cursor's catalog: this repo is also a Cursor plugin (.cursor-plugin/ and mcp.json: the server plus the skills). Until it is listed in the Cursor Marketplace, use the setup guide, or give Grok Bot the server URL (guide).
  • Anything else: point it at the server URL above. Full MCP docs.

What your assistant can do

  • Draft a post in each account's own voice. It reads that account's recent posts first.
  • Schedule or publish, per account or as a campaign across several accounts.
  • Attach images, video and PDFs, and manage the media library.
  • See the calendar, list and search posts, and retry a failed one.
  • Report performance per post and per account: impressions or views, likes, comments, shares and reach, plus saves, link clicks, profile visits, follows and watch time where the platform reports them, and daily follower counts per connected account. A metric a platform doesn't report shows as blank, never as zero.

Each platform's own rules apply: Instagram and Pinterest need an image or video, TikTok and YouTube need a video, and Instagram needs a Creator or Business account. Tool reference.

Antwork Skills for Claude Code and claude.ai

This repo also adds Agent Skills on top of the connector. The connector alone handles single steps: drafting, scheduling, publishing, media, connections. The skills cover the multi-step workflows: a content calendar planned around what's already scheduled, one piece repurposed across platforms, a campaign arc, ideas grounded in what performed, an analytics report, and a scored audit. One router sends /antwork <command> (or a plain request) to the right one.

Commands

CommandSkillWhat it does
/antwork voice [account]antwork-voiceRead an account's voice from its real posts, or capture one from samples.
/antwork calendar <theme>antwork-calendarPlan and batch-schedule a content calendar.
/antwork repurpose <source>antwork-repurposeOne piece → one post with a native version per platform.
/antwork campaign <goal>antwork-campaignSequence a multi-post campaign / launch week.
/antwork ideas [topic]antwork-ideasData-driven hooks grounded in what already performed.
/antwork analytics [range]antwork-analyticsPull performance + engagement and synthesize a report.
/antwork auditantwork-auditFull social-presence audit with 5 parallel agents + a 0-100 Social Health Score.
/antwork ship [--since …] [--release <tag>]antwork-shipTurn the current repo's commits, merged PRs or a release into build-in-public posts, per account, in each account's voice.

You don't have to type the command — describe the intent ("plan next week", "how did last month do?") and the router picks the skill. A single post, connecting an account and media need no skill: the connector's own instructions cover them.

The audit's parallel agents

In Claude Code, /antwork audit spawns five read-only subagents concurrently, then synthesizes a weighted score. On claude.ai, which has no subagents, the same five dimensions run one after another:

AgentDimensionWeight
antwork-performanceEngagement & top/bottom posts30%
antwork-voice-analystVoice consistency across accounts20%
antwork-cadencePosting cadence & timing20%
antwork-contentContent quality (hooks, CTAs, fit)20%
antwork-growthPlatform coverage & growth10%

Prerequisite

The skills call the Antwork MCP server, so it has to be connected (see Connect). The plugin does that for you. A single OAuth token spans all your workspaces.

Once connected, a good first run is audit (where you stand), then ideas or calendar (what to post next).

Install the skills

Claude Code plugin (recommended)

This repo is also a Claude Code plugin marketplace. Installing the plugin wires up the Antwork MCP server and all skills + agents in one step:

sh
/plugin marketplace add polynode-co/antwork/plugin install antwork@antwork

That's it — the antwork MCP server connects automatically (complete the OAuth prompt), and the router, 8 skills, and 5 audit agents load. Why the plugin over loose skills: the skills are useless until Antwork's MCP is connected, and the plugin ships that config bundled, so there's no separate connector setup.

Script install (no plugin)

If you'd rather not use the plugin system, the script copies the skills + agents straight into ~/.claude/ (you still connect the Antwork MCP yourself):

sh
curl -fsSL https://raw.githubusercontent.com/polynode-co/antwork/main/install.sh | bash

Prefer to clone first? git clone … && cd antwork-skills && ./install.sh. Remove everything with ./uninstall.sh.

OpenClaw

clawhub/antwork/ is a self-contained skill for OpenClaw. A ClawHub listing is coming soon; it is not published there yet, so clawhub install won't find it. Until then, install it by hand: copy the folder into your OpenClaw skills directory and connect the server.

sh
git clone https://github.com/polynode-co/antwork.gitcp -r antwork-skills/clawhub/antwork ~/.openclaw/skills/antworkmcporter config add antwork --url https://api.antwork.io/mcp --auth oauth

It is deliberately not the router above. ClawHub publishes one folder, so a skill that routes to 8 siblings that were never installed would be broken — this one inlines the setup, the drafting protocol, the character limits and the draft→publish two-step in a single file.

claude.ai

Plugins are Claude Code only, so claude.ai gets the same skills as one upload:

  1. Download antwork-claude-ai-skill.zip.
  2. In claude.ai, open Settings, find Skills, and upload the ZIP.
  3. Connect the Antwork connector (see Connect) if you haven't.

It is one skill named antwork: the router, with every other skill and audit dimension inside it as a reference file it reads when needed. claude-ai/build.sh generates it from skills/ (each skill with its templates, and the audit's agents), and a workflow republishes it on every change, so it never drifts from the plugin. Posting itself needs no skill on claude.ai either: the connector sends its drafting rules when it connects.

Repository layout

antwork-skills/├── .claude-plugin/│   ├── plugin.json           # plugin manifest│   └── marketplace.json      # self-hosted marketplace (lists this plugin)├── .mcp.json                 # Antwork MCP server — bundled & auto-connected├── .cursor-plugin/           # Cursor plugin manifest + single-plugin marketplace├── mcp.json                  # the same server, for the Cursor plugin├── skills/                   # router + 8 specialized skills, each with its own templates/│   ├── antwork/              # router — /antwork <command>│   ├── antwork-ship/         # commits / PRs / releases → posts│   ├── antwork-calendar/     ├── antwork-campaign/│   ├── antwork-repurpose/    ├── antwork-ideas/│   ├── antwork-voice/        ├── antwork-analytics/│   └── antwork-audit/        # + agents/: the 5 parallel audit subagents├── claude-ai/build.sh        # builds the claude.ai ZIP from skills/├── clawhub/                  # self-contained OpenClaw skill (ClawHub listing coming soon)├── install.sh / uninstall.sh # script-install fallback└── README.md / LICENSE

Contributing

Each skill lives in skills/<name>/SKILL.md with YAML frontmatter (name, description) followed by markdown instructions. Keep description: specific — it determines when Claude auto-loads the skill. Use only real Antwork MCP tools and never invent tool arguments; the server rejects unknown fields.

License

MIT

Source: README.md at commit 585cc85

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

3
  1. v1.0.4LatestOct 29, 2026
  2. v1.0.3Oct 14, 2026
  3. v1.0.2Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts