io.github.4hmetuyar/toxic-flow-auditor
guardbee-toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
alive probed 2026-10-14
5tools
748tokens in Claude Opus 5.5
823tokens in Claude Code
0.4 %of a 200k context window
393o200k_base estimate
398 msto initialize
10 msto list tools
- Run it
- npx -y @guardbee/mcp-toxic-flow-auditor@0.1.4 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- guardbee-toxic-flow-auditor 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 2026-10-02 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| audit_catalog | 119 | 30 % |
| scan_directory | 94 | 24 % |
| scan_source | 78 | 20 % |
| scan_file | 52 | 13 % |
| explain_trifecta | 50 | 13 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.4hmetuyar/toxic-flow-auditor)
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.