mcpcost

io.github.GuardBee/reverse-shield

guardbee-reverse-shield

Is the io.github.GuardBee/reverse-shield MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-10.

Audits shipped apps for how easily they can be reverse engineered

alive probed 2026-11-14 · unchanged since 2026-11-10

4tools
1.3ktokens in Claude Opus 5.5
0.7 %of Claude's 200k window
0.5×the median server
418 msto initialize
34 msto list tools
Run it
npx -y @guardbee/mcp-reverse-shield@0.8.0 (stdio, probed in a container with the network off)
Host
npmjs.com
Reports itself as
guardbee-reverse-shield 0.1.0
Capabilities
tools
Instructions
none
Of a 1M window
0.1 % of a 1M context window
Count
1.3k tokens in Claude Opus 5.5, exact, measured 2026-10-31. With the Claude Code prefix mcp__…__ on each tool name: 1.4k. The o200k_base estimate is 766. Counted again when the tool definitions change. Method.
Repository
https://github.com/GuardBee/guardbee-mcp
Registry
active, updated 2026-11-10 · registry entry
Changes
2 recorded, reachable in 2 of them. A row is added when the result, the tool count or the cost changes.

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.72×.

Tool≈ Claude tokenso200k estimateShare of this server
scan_artifact65337949 %
scan_url28816722 %
suggest_fixes27716121 %
list_checks102598 %

Compare this server with others.

More servers

Other registry entries on npmjs.com, the ones next to this name; all of them.

Servers that mention reverse.

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-31 07:34alive404 ms41.3k766
2026-10-29 07:44alive418 ms41.3k774

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