# @guardbee/mcp-toxic-flow-auditor

Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.1.14
- **Author:** io.github.GuardBee
- **License:** MIT
- **npm:** @guardbee/mcp-toxic-flow-auditor
- **Source:** https://github.com/GuardBee/guardbee-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-10T07:01:48.689Z
- **Version scanned:** 0.1.14
- **CVEs:** none found by OSV at scan time

## Tools

20 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `fetch_url` — Download a page
- `get_secret` — Read from vault
- `lookup_customer` — KVKK kapsamındaki müşteri kaydını getir
- `send_email` — Notify user
- `fetch_page` — Scrape a URL
- `read_vault_secret` — Read API key from vault
- `send_slack_message` — Post to webhook
- `list_patterns` — List scanner rules
- `scan_text` — Scan a string
- `get_db_row` — Read database users
- `export_csv` — Export and upload report
- `research_and_mail_secrets` — Fetch a URL, read vault secrets, and send email with findings
- `read_customer_db` — SQL select from müşteri table
- `drop_table` — Drop a database table
- `name` — description
- `audit_catalog` — Audit a tools/list-shaped JSON catalog for the lethal trifecta (toxic flow): untrusted content + sensitive/private data + exfiltration or destruction on the sam
- `scan_source` — Scan TypeScript/JavaScript MCP server source for .tool(...) registrations and audit them for toxic flows
- `scan_file` — Scan a single source file for toxic flows
- `scan_directory` — Recursively scan a directory of MCP server source for toxic flows across all registered tools
- `explain_trifecta` — Explain the lethal trifecta / toxic-flow model this auditor uses

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp-toxic-flow-auditor\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@guardbee/mcp-toxic-flow-auditor\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on your machine.
- Floor 36, ceiling 60 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40guardbee%2Fmcp-toxic-flow-auditor
- Install plan: https://forgeregistry.com/api/v1/packages/%40guardbee%2Fmcp-toxic-flow-auditor/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40guardbee%2Fmcp-toxic-flow-auditor
- HTML page: https://forgeregistry.com/registry/%40guardbee%2Fmcp-toxic-flow-auditor
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.