ShapelessAI← All apps

Claude Codeby Anthropic

Connect Claude Code to your LinkedIn, X, Instagram and 6 more

About a minute, three moves. Then Claude Code writes, designs, renders video, schedules and publishes for you, and you approve. Works in the terminal, the desktop app and the VS Code and JetBrains extensions.

Which network?

Add Shapeless to Claude Code

In Claude Code, add Shapeless with the URL below. A Shapeless tab opens: sign in (or create an account) and allow. That is the whole install; nothing to download, no API key.

  1. 1
    Add the server once, for every project
    Add the server once, for every projectclaude mcp add --transport http --scope user shapeless https://shapelessai.com/mcp
  2. 2

    In a session, run /mcp, pick shapeless and choose Authenticate. A browser tab opens: sign in and allow.

  3. 3
    Or sign in from the shell
    Or sign in from the shellclaude mcp login shapeless

Steps read from Connect Claude Code to tools via MCP on . Vendors move menus; if a step no longer matches, the source is the place to check and hello@shapelessai.com is where to tell us.

Connect your social accounts to Shapeless, once

In Shapeless, open Accounts and connect each account through the platform's own sign-in. Shapeless keeps that connection; Claude Code never sees a password or token for it.

Open Accounts in Shapeless →

Ask Claude Code in plain words

Ask in the session. To hand a web conversation over, paste its id: the /continue prompt loads the brief and carries on there. Every draft lands in your Shapeless queue for approval unless you say otherwise, and you are asked before anything goes out.

  • Write a LinkedIn post announcing our new pricing page. Founder voice, no hashtags, and make a 6-slide PDF carousel to go with it.
  • Draft a thread on X about why we rebuilt onboarding, six posts, with the demo GIF on the first.
  • Make an Instagram Reel from this feature: 20 seconds, captions on, our voice, vertical.

Questions

Which Claude Code plans can add Shapeless?
Any Claude plan that runs Claude Code. The connector is per user, so it follows you into every project.
How do I use it once it is connected?
Ask in the session. To hand a web conversation over, paste its id: the /continue prompt loads the brief and carries on there.
Does Claude Code ask before publishing?
Not unless you set a standing agent to auto-publish. A job proposes drafts and waits for your approval in Shapeless or in the chat; the tools that approve, publish or spend are flagged, so Claude Code asks you before running one.
Do I need a developer app or API key for each network?
No. You connect each account to Shapeless once, under Accounts, through the network's own sign-in. Shapeless holds those connections; Claude Code signs in to Shapeless with OAuth and never sees a network token or password.
How do I disconnect it?
Settings → API keys → Connected apps in Shapeless lists Claude Code with a Disconnect button; revoking there ends its access at once. Claude Code also lets you remove the connector on its side.
For developers and agents: the MCP server, the tools, the CLI
Remote MCP server URL
https://shapelessai.com/mcp

A remote MCP server over streamable HTTP. Sign-in is OAuth 2.1 with dynamic client registration and PKCE, so any host - Claude Code or your own agent - registers itself and opens a Shapeless tab to sign in and allow; the resource metadata is at /.well-known/oauth-protected-resource. Read tools run freely; anything that publishes, spends or overwrites is flagged destructive so the host asks first. The token is revocable under Settings → API keys → Connected apps.

ToolWhat it doesRuns
meWho this credential belongs to: email, plan, credit balance.reads
connections_listConnected social accounts (identity only, no tokens).reads
jobs_createStart a durable job from a goal, optionally with files attached. The run keeps going server-side; returns the job id and its web url to poll or continue.drafts
jobs_listList jobs with liveness and the web url of each, 200 per page, newest first. A non-null nextCursor means older jobs exist: pass it back as before.reads
jobs_getOne job in full: transcript, running/idle status, outputs (posts with queue state, media) and its web url. Use jobs_brief when you only need enough to reply.reads
jobs_briefCompact context for continuing a conversation: the last messages clipped, an artifact inventory, post statuses, and the web url. Use jobs_get for the full transcript, jobs_continue to reply.reads
jobs_tailWatch a job's run: replays its events from the cursor, then follows live until the run ends, 60 seconds pass, or 200 events. Returns {live, cursor, events} - resume with that cursor. {live: false} means no run stream to attach to; the job may still have finished work, so read jobs_get.reads
jobs_continueSend another message to a job, optionally with files attached - also the way to resume a stuck or failed run with full history.drafts
jobs_stopStop a running job.asks you first
posts_listThe post queue: proposed drafts, scheduled posts, published history.reads
posts_getOne post's live state.reads
posts_approvePUBLISHES CONTENT: approving moves proposals to the schedule, and they will go out.asks you first
posts_dismissDismiss proposed posts - nothing goes out.asks you first
posts_publishPUBLISHES CONTENT NOW: pushes a queued post to the platform immediately.asks you first
characters_listThe account's actors: who they are, what their voice is, and which parts are locked. voiceDescription is the casting direction a designed voice was written from - read it before designing another one, and reuse the actor that already fits.reads
characters_voiceSPENDS CREDIT: gives an actor a voice. description designs one from casting direction (kept on the character, so later runs can reuse the actor); sampleMediaKey clones a real voice and requires consent: true - the user's own attestation that they hold the rights. Returns the voice id, a preview clip and what it cost.asks you first
brain_treeBrand Memory's file list with the completion ring.reads
brain_readRead one Brand Memory file.reads
brain_writeWrite one Brand Memory file (.md paths only) - the agent grounds future posts in it.asks you first
assets_listThe media library: brand uploads and generated media.reads
agents_listThe agent roster (the API calls them strategies).reads
agents_saveCreate an agent (no id) or edit one (with id). Setting autoPublishPosts arms publishing without human approval and needs the publish scope; everything else needs write.asks you first
agents_wakePUBLISH-SCOPED: wake an agent now; it plans and proposes (or with auto-publish, posts) immediately. Returns the conversation it woke into and its web url.asks you first

The same account is driveable from a terminal or a script with a scoped API key: npx shapelessai --help, or the REST API documented in the public agent repo. Keys are minted under Settings → API keys.