io.github.GuardBee/prompt-leak-scanner
guardbee-prompt-leak-scanner
Catches leaked credentials and PII in outbound LLM prompts
alive probed 2026-10-14
5tools
971tokens in Claude Opus 5.5
1.0ktokens in Claude Code
0.5 %of a 200k context window
557o200k_base estimate
440 msto initialize
17 msto list tools
- Run it
- npx -y @guardbee/mcp-prompt-leak-scanner@0.1.19 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- guardbee-prompt-leak-scanner 0.1.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/GuardBee/guardbee-mcp
- Registry
- active, updated 2026-10-14 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| scan_directory | 164 | 29 % |
| scan_messages | 132 | 24 % |
| scan_text | 129 | 23 % |
| scan_file | 83 | 15 % |
| list_patterns | 49 | 9 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.GuardBee/prompt-leak-scanner)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.