MCP server for interacting with your LINE Official Account
Server has 5 tools with complete schemas and descriptions. Naming follows verb_noun convention (push_, broadcast_, get_). Descriptions are present and contextual (avg ~150 chars). However, critical gaps exist: (1) No output schemas documented, LLMs cannot predict response structure; (2) Broadcast tools lack confirmation/dry-run pattern despite DESTRUCTIVE risk; (3) Error messages are generic ('Failed to push message: {error.message}') and do not guide recovery; (4) No tool annotations (destructiveHint, readOnlyHint) despite clear risk stratification; (5) userId parameter defaults to env var but lacks validation, if DESTINATION_USER_ID is unset, tool silently fails with generic error instead of actionable guidance.
Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts. Please be aware that this message will be sent to all users.
Broadcast a simple text message via LINE to all users who have followed your LINE Official Account. Use this for sending plain text messages without formatting. Please be aware that this message will be sent to all users.
Get detailed profile information of a LINE user including display name, profile picture URL, status message and language.
Push a highly customizable flex message to a user via LINE. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts.
Push a simple text message to a user via LINE. Use this for sending plain text messages without formatting.
No output schemas documented. LLMs cannot predict response structure or plan downstream calls. Tools return JSON.stringify(response) without field documentation.
Broadcast tools (broadcast_text_message, broadcast_flex_message) marked DESTRUCTIVE but lack confirmation/dry-run pattern. Agents can accidentally broadcast to all users without safeguard.
Error messages are generic and non-actionable. 'Failed to push message: {error.message}' does not guide LLM recovery. Should include: what went wrong, why, and what to try next.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
No tool annotations (destructiveHint, readOnlyHint, idempotentHint). Tools have clear risk levels (WRITE, DESTRUCTIVE, READ_ONLY) but do not declare them in schema.
userId parameter defaults to DESTINATION_USER_ID env var but lacks validation. If env var is unset, tool returns generic error 'Specify the userId or set DESTINATION_USER_ID' instead of failing fast with clear guidance.