io.github.GuardBee/toxic-flow-auditor
NPM · @GUARDBEE/MCP-TOXIC-FLOW-AUDITOR
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Available components
Last scanned (18 hours ago)
Scores higher than 79% of npm servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to GuardBee/guardbee-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 231 tokens (~46/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage79
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 38% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +43
- Injection markers: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Dependency health: unverified → 0.86 ▲ functional
- Stability: unverified → 0.27 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 22 Oct 26 −42
- Known CVEs: partial → unverified ▼ security
- Stability: 0.20 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Dependency health: partial → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Security disclosure: fail → pass ▲ functional
- Package version: 0.1.26 → 1.0.2 functional
- Package version: 0.1.26 → 1.0.1 functional
- Package version: 0.1.26 → 1.0.0 functional
- 21 Oct 26 +11
- Known CVEs: unverified → partial ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → partial ▲ functional
- Dependency health: unverified → 0.85 ▲ functional
- Package version: 0.1.25 → 0.1.26 functional
- 20 Oct 26 −10
- Known CVEs: pass → unverified ▼ security
- Dependency health: 0.85 → unverified ▼ functional
- Package version: 0.1.22 → 0.1.25 functional
- Package version: 0.1.23 → 0.1.24 functional
- Package version: 0.1.22 → 0.1.23 functional
- 19 Oct 26 0
- Package version: 0.1.22 → 0.1.23 functional
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +30
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.07 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Tool coverage: 38 functional
- First check of Schema quality: pass functional
- First check of Schema quality: good functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Oct 2026 · Analysed npm/@guardbee/mcp-toxic-flow-auditor@1.0.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | GuardBee/guardbee-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/GuardBee/guardbee-mcp/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 3386365075 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:da510c85b18ea5857d3408c70c24b43d610f420284f4205237e90083094861bf6f27212575d5e9c9112faf2079186cf980ecf0c52560ea76ea0386901 |
Background: How many MCP packages publish verified provenance →
Dependencies 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_catalog ~85
Audit a tools/list-shaped JSON catalog for the lethal trifecta (toxic flow): untrusted content + sensitive/private data + exfiltration or destruction on the same MCP server. Returns an A–F grade.
| Name | Type | Req | Description |
|---|---|---|---|
| catalog | string | yes | JSON array of tools, or { tools: [...] } from tools/list |
| label | string | – | Optional label for the server/catalog |
No output schema declared.
No examples provided.
explain_trifecta ~23
Explain the lethal trifecta / toxic-flow model this auditor uses
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
scan_directory ~47
Recursively scan a directory of MCP server source for toxic flows across all registered tools
| Name | Type | Req | Description |
|---|---|---|---|
| exclude | array | – | – |
| maxFiles | integer | – | – |
| path | string | yes | – |
No output schema declared.
No examples provided.
scan_file ~24
Scan a single source file for toxic flows
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
No output schema declared.
No examples provided.
scan_source ~52
Scan TypeScript/JavaScript MCP server source for .registerTool(...) and .tool(...) registrations and audit them for toxic flows
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Source code to scan |
| label | string | – | – |
No output schema declared.
No examples provided.
How do I install the io.github.GuardBee/toxic-flow-auditor MCP server?
io.github.GuardBee/toxic-flow-auditor runs locally as an npm package, launched with npx -y @guardbee/mcp-toxic-flow-auditor. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @guardbee/mcp-toxic-flow-auditor
claude mcp add guardbee-toxic-flow-auditor -- npx -y @guardbee/mcp-toxic-flow-auditor
What is the io.github.GuardBee/toxic-flow-auditor MCP server?
io.github.GuardBee/toxic-flow-auditor is an MCP server listed in the public MCP registry as io.github.GuardBee/toxic-flow-auditor. Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress. This page covers its npm package (@guardbee/mcp-toxic-flow-auditor).
Is the io.github.GuardBee/toxic-flow-auditor MCP server safe to use?
io.github.GuardBee/toxic-flow-auditor scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.GuardBee/toxic-flow-auditor MCP server expose?
io.github.GuardBee/toxic-flow-auditor exposes 5 tools: audit_catalog, scan_source, scan_file, scan_directory, explain_trifecta. Their descriptions and schemas cost roughly 231 tokens of context every time the server is loaded.
Is the io.github.GuardBee/toxic-flow-auditor MCP server still maintained?
io.github.GuardBee/toxic-flow-auditor is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.GuardBee/toxic-flow-auditor MCP server under?
io.github.GuardBee/toxic-flow-auditor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.