Typefully for AI agents

Typefully drafts and schedules social content, used by writers and creators who plan posts ahead of time and queue them across accounts. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Social mediaAPI keyMCP + RESTtypefully.com
AUDIT LOG · TYPEFULLYPOLICY: acme-support
09:41:07 · claude · u_8f2read
typefully.list_tags
List Tags✓ allowed · 212ms
09:41:08 · claude · u_8f2read
typefully.get_draft
Get Draft✓ allowed · 164ms
09:41:09 · claude · u_8f2write
typefully.create_tag
Create Tag✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
typefully.delete_draft
Delete Draft✕ blocked · policy: deny
EVERY TYPEFULLY CALL, ON THE RECORD
01 · USE CASES

What agents do in Typefully.

01

Create a draft post

Write a new draft for an upcoming post, ready for review before it's queued.

02

Get the posting queue

Pull the current scheduled queue as a read-only check before adding to it.

03

Confirm before deleting a draft

Check with the user before deleting a draft, since unpublished work would be lost.

02 · ACTIONS

16 Typefully actions, graded by risk.

Every Typefully action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

10

Look things up. Allowed by default.

  • typefully.get_draft
    Get Draft
  • typefully.get_queue
    Get Queue
  • typefully.list_tags
    List Tags
  • typefully.list_drafts
    List Drafts
  • typefully.get_social_set
    Get Social Set
  • typefully.get_current_user
    Get Current User
  • typefully.get_media_status
    Get Media Status
  • typefully.list_social_sets
    List Social Sets
  • typefully.get_queue_schedule
    Get Queue Schedule
  • typefully.resolve_linked_in_organization
    Resolve LinkedIn Organization

write

5

Create and change things. Allow, or ask the user first.

  • typefully.create_tag
    Create Tag
  • typefully.create_draft
    Create Draft (v2)
  • typefully.update_draft
    Update Draft
  • typefully.update_queue_schedule
    Update Queue Schedule
  • typefully.initialize_media_upload
    Initialize Media Upload

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • typefully.delete_draft
    Delete Draft
03 · HOW IT WORKS

Typefully in three steps.

  1. 01Your users connect TypefullyThey add their Typefully api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Draft” can be denied outright.
  3. 03Any agent can actYour agent calls Typefully through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('typefully', {
  read: 'allow',
  write: 'ask',        // create_tag
  destructive: 'deny',  // delete_draft
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Typefully connects.

Users add their Typefully api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Typefully connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Typefully from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Typefully and Arc0, answered.

Q01

Can I use Typefully with Claude, ChatGPT or Cursor?

Yes. Connect Typefully to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Typefully actions you allow.

Q02

How do users connect Typefully?

Users add their Typefully api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Typefully actions can my agent take?

16 in total: 10 read, 5 write and 1 destructive, such as “create Tag”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Typefully?

Yes. Actions like “delete Draft” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Typefully too?

Yes. The same Typefully connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Typefully into your agent.

Your users connect Typefully once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan