LINE for AI agents

LINE is a messaging platform popular in Asia, used here through its Messaging API to send messages and manage a business account's audience. 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.

CommunicationAPI keyMCP + RESTline.me
AUDIT LOG · LINEPOLICY: acme-support
09:41:07 · claude · u_8f2read
line.list_rich_menus
List Rich Menus✓ allowed · 212ms
09:41:08 · claude · u_8f2read
line.get_rich_menu
Get Rich Menu✓ allowed · 164ms
09:41:09 · claude · u_8f2write
line.create_rich_menu
Create Rich Menu✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
line.delete_rich_menu
Delete Rich Menu✕ blocked · policy: deny
EVERY LINE CALL, ON THE RECORD
01 · USE CASES

What agents do in LINE.

01

Reply to a customer message

Send a reply to a customer's message within an active LINE conversation.

02

Check message delivery counts

Look up how many messages were delivered on a given day, a read-only check.

03

Approve before a broadcast push

Require approval before sending a push message to all followers, since it reaches the entire audience.

02 · ACTIONS

15 LINE actions, graded by risk.

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

read

6

Look things up. Allowed by default.

  • line.get_rich_menu
    Get Rich Menu
  • line.list_rich_menus
    List Rich Menus
  • line.list_follower_ids
    List Follower IDs
  • line.list_chat_member_ids
    List Chat Member IDs
  • line.get_message_delivery_count
    Get Message Delivery Count
  • line.download_message_content_preview
    Download Message Content Preview

write

7

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

  • line.create_rich_menu
    Create Rich Menu
  • line.send_push_message
    Send Push Message
  • line.create_rich_menu_with_image
    Create Rich Menu with Image
  • line.reply_to_message
    Reply to Message
  • line.mark_messages_as_read
    Mark Messages as Read
  • line.upload_rich_menu_image
    Upload Rich Menu Image
  • line.link_or_unlink_user_rich_menu
    Link or Unlink User Rich Menu

destructive

2

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

  • line.delete_rich_menu
    Delete Rich Menu
  • line.set_or_clear_default_rich_menu
    Set or Clear Default Rich Menu
03 · HOW IT WORKS

LINE in three steps.

  1. 01Your users connect LINEThey add their LINE api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Rich Menu” can wait for the user, and “delete Rich Menu” can be denied outright.
  3. 03Any agent can actYour agent calls LINE 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('line', {
  read: 'allow',
  write: 'ask',        // create_rich_menu
  destructive: 'deny',  // delete_rich_menu
})

# 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 LINE connects.

Users add their LINE 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 LINE 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 LINE from any agent.

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

LINE and Arc0, answered.

Q01

Can I use LINE with Claude, ChatGPT or Cursor?

Yes. Connect LINE 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 LINE actions you allow.

Q02

How do users connect LINE?

Users add their LINE 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 LINE actions can my agent take?

15 in total: 6 read, 7 write and 2 destructive, such as “create Rich Menu”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in LINE?

Yes. Actions like “delete Rich Menu” 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 LINE too?

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

Get started

Plug LINE into your agent.

Your users connect LINE once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.

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