LINE BotSAFE
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
日本語版 READMEはこちら
[](https://www.npmjs.com/package/@line/line-bot-mcp-server)
Model Context Protocol (MCP) server implementation that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
[!NOTE] This repository is provided as a preview version. While we offer it for experimental purposes, please be aware that it may not include complete functionality or comprehensive support.
Tools
- push_text_message
- Push a simple text message to a user via LINE.
- Inputs:
userId(string?): The user ID to receive a message. Defaults to DESTINATIONUSERID. EitheruserIdorDESTINATION_USER_IDmust be set.message.text(string): The plain text content to send to the user.- push_flex_message
- Push a highly customizable flex message to a user via LINE.
- Inputs:
userId(string?): The user ID to receive a message. Defaults to DESTINATIONUSERID. EitheruserIdorDESTINATION_USER_IDmust be set.message.altText(string): Alternative text shown when flex message cannot be displayed.message.contents(any): The contents of the flex message. This is a JSON object that defines the layout and components of the message.message.contents.type(enum): Type of the container. 'bubble' for single container, 'carousel' for multiple swipeable bubbles.- broadcast_text_message
- Broadcast a simple text message via LINE to all users who have followed your LINE Official Account.
- Inputs:
message.text(string): The plain text content to send to the users.- broadcast_flex_message
- Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account.
- Inputs:
message.altText(string): Alternative text shown
600c41c913c5OBSERVED · 2026-09-27Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add line-bot-mcp-server --env CHANNEL_ACCESS_TOKEN=${CHANNEL_ACCESS_TOKEN} -- npx -y @line/[email protected]{
"mcpServers": {
"line-bot-mcp-server": {
"command": "npx",
"args": [
"-y",
"@line/[email protected]"
],
"env": {
"CHANNEL_ACCESS_TOKEN": "${CHANNEL_ACCESS_TOKEN}"
}
}
}
}Exposed tools (13)
8 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
broadcast_flex_message | read | |
broadcast_text_message | read | |
cancel_rich_menu_default | read | |
create_rich_menu | write | |
delete_rich_menu | destructive | |
get_follower_ids | read | |
get_group_summary | read | |
get_message_quota | read | |
get_profile | read | |
get_rich_menu_list | read | |
push_flex_message | write | |
push_text_message | write | |
set_rich_menu_default | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
delete_rich_menu
.prettierrc.json
import { flexMessageSchema } from "../../../src/common/schema/flexMessage.js";import { USER_AGENT } from "../../src/version.js";new URL("../../dist/index.js", import.meta.url),import BroadcastFlexMessage from "../../src/tools/broadcastFlexMessage.js";
import BroadcastTextMessage from "../../src/tools/broadcastTextMessage.js";
baseUrl: `http://127.0.0.1:${address.port}`,@line/bot-sdk, @marp-team/marp-core, puppeteer, zod, @modelcontextprotocol/server, @modelcontextprotocol/client, @types/node, prettier
Gates applied: no_behavioural_pass.
600c41c913c5full audit observations/trust-audit/mcp-server/line__line-bot.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-27 | 600c41c913c5 | SAFE | B | 89 | first audit |
Questions
What is the LINE Bot MCP server?
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
What tools does LINE Bot expose?
13 in total: 8 read-only, 4 that write, and 1 that can delete or overwrite (delete_rich_menu). Every one is listed on this page with its risk.
Is LINE Bot safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does LINE Bot need?
It reads CHANNEL_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (600c41c913c5), read on 2026-09-27. The repository is watched and re-audited when it changes.