Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SUPABASE_URLNoSupabase project URL. Required for the queue tools. `NEXT_PUBLIC_SUPABASE_URL` is accepted too, so a Next.js `.env.local` works as is.
LINE_MCP_ALLOW_BROADCASTNoSet to `true` to register the `line_broadcast` tool.
LINE_CHANNEL_ACCESS_TOKENNoLong-lived channel access token. Required for the LINE tools.
SUPABASE_SERVICE_ROLE_KEYNoSupabase service role key. Server-side only. Never ship it to a browser. Required for the queue tools.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
line_bot_infoA

Basic info about the LINE Official Account this bot runs on: display name, basic ID, chat mode.

line_message_quotaA

Monthly push/broadcast message quota and how much of it has been used this month.

line_followers_insightA

Follower statistics for one day: followers, targeted reaches, blocks. LINE computes these per day in UTC+9 and only after the day ends.

line_get_profileA

Display name, picture and status message of a user who has added the bot as a friend.

line_richmenu_listB

All Rich Menus on the channel, plus which one is the default for every user.

line_queue_healthA

Health of the webhook job queue (line_jobs): count per status, age of the oldest pending job, and jobs stuck in processing. Use this first when users say the bot is not replying.

line_failed_jobsB

Most recent failed jobs with their error, event type and message text.

line_find_usersB

Search linked users (line_users) by display name and/or role.

line_retry_jobA

Put a failed job back to pending so the next worker run picks it up. Reply tokens expire soon after the event, so a job that replies may fail again; push is the fallback.

line_push_textA

Send a text message to one user, group or room. Counts against the monthly message quota.

line_link_richmenuA

Show a specific Rich Menu to one user, e.g. after a role change. Pass richMenuId null to remove the per-user menu so the default shows again.

line_broadcastA

Send a text message to EVERY friend of the account. Uses one message of quota per recipient and cannot be undone.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct operation: user lookup vs profile retrieval, push vs broadcast, queue health vs failed job listing vs retry, and rich menu listing vs linking. Overlaps are minimal and descriptions clearly differentiate scope.

Naming Consistency3/5

All tools share a 'line_' prefix and snake_case, but the naming pattern mixes verb_noun (line_find_users, line_get_profile) with noun_noun or noun_list (line_bot_info, line_message_quota, line_richmenu_list). The inconsistency is still readable but not fully predictable.

Tool Count5/5

12 tools is well-scoped for LINE bot operations, covering messaging, monitoring, user lookup, and rich menu management without redundancy. Each tool earns its place.

Completeness4/5

The surface covers core ops like sending messages, monitoring quota and queues, retrying jobs, and inspecting users. Minor gaps exist: rich menu creation/deletion, non-text message types, and group/room management are missing but likely out of scope.

Maintenance

ActivityMaintained
ResponsivenessNo issues