mcpcost

io.github.Ranqint/vibescale

VibeScale

Is the VibeScale MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-13.

Pre-launch checks for AI-built apps: leaked keys, Supabase RLS gaps, browser-exposed env vars.

alive probed 2026-11-14 · unchanged since 2026-11-13 · HTTP 200

3tools
1.0ktokens in Claude Opus 5.5
0.5 %of Claude's 200k window
0.4×the median server
1.5 sto initialize
114 msto list tools
Endpoint
https://vibe.elya-studio.com/mcp (streamable-http)
Host
vibe.elya-studio.com
Protocol
2025-11-25
Reports itself as
vibescale 1.0.0
Capabilities
tools
Instructions
431 characters
Of a 1M window
0.1 % of a 1M context window
Count
1.0k tokens in Claude Opus 5.5, exact, measured 2026-11-13. With the Claude Code prefix mcp__…__ on each tool name: 1.0k. The o200k_base estimate is 595. Counted again when the tool definitions change. Method.
Website
https://vibe.elya-studio.com/tools/chatgpt-claude
Registry
active, updated 2026-11-12 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.70×.

Tool≈ Claude tokenso200k estimateShare of this server
scan_app_launch_readiness36521536 %
check_env_exposure33619833 %
lint_supabase_rls30918231 %

Compare this server with others.

More servers

Servers that mention supabase or browser.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher

Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.