Wraps MultiviewGrid's REST API + Chrome DevTools Protocol so any agent (HAG, Claude, etc.) can control a running MultiviewGrid instance.
Server has 6 tools with basic schemas and descriptions, but significant gaps in parameter documentation and error handling. Tool names follow verb_noun convention (multiview_*), but descriptions are minimal (10-50 chars, well below the 194-char baseline). Most parameters lack descriptions entirely. No output schemas documented. Error handling is absent, tools return raw API responses or generic errors without recovery guidance. This is a typical community STDIO server with incomplete definitions.
Trigger auto-start of all streams (starts playback).
Check if the MultiviewGrid API server is running.
Capture a screenshot of the current MultiviewGrid window. Returns the file path.
Add a new stream to the grid.
Remove a stream from the grid by ID.
List all streams in the current grid.
Parameter descriptions missing or minimal. 'stream_id', 'output_path', 'name', 'stream_url', 'logo_url', 'is_muted' lack descriptions explaining format, constraints, or examples. LLMs cannot infer parameter meaning from names alone.
Tool descriptions are too short (10-50 chars vs 194-char baseline). 'Check if the MultiviewGrid API server is running' and 'List all streams in the current grid' lack context on WHEN to call them, WHAT they return, or HOW to use results downstream.
No output schemas documented. Tools return raw API responses (JSON objects) but LLMs have no schema to understand what fields to expect. Downstream tool calls cannot be planned without guessing response structure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | 2026-07-28+ | v2 |
Error handling absent. _api_request() returns raw HTTP errors or generic exception strings ('error': str(e)). No recovery guidance, categorization (retryable vs fatal), or actionable messages. LLMs cannot self-correct.
Destructive tool (multiview_stream_delete) has no confirmation or dry-run support. Agents can delete streams without verification, risking accidental data loss.