Glin Profanity MCP
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a purpose-aligned profanity moderation MCP, but users should verify the external npm package and understand its user-tracking behavior before use.
This skill looks coherent for profanity and moderation workflows. Before installing, confirm that you trust the npm package and maintainer, and review how the tracking/profile tools store or delete moderation history.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the MCP configuration may run code fetched from npm, so the user is trusting that package and its future updates.
The setup runs an external npm package via npx without pinning a version. This is a common MCP installation pattern and fits the stated purpose, but the package code was not included in the artifacts reviewed here.
"command": "npx", "args": ["-y", "glin-profanity-mcp"]
Verify the npm/GitHub package before installing, consider pinning a known version, and only add it to MCP clients you trust.
Moderation histories may contain sensitive user content or influence future moderation decisions if reused.
These tools imply storing or accumulating user moderation history. That is relevant to the moderation purpose, but the artifact does not specify retention, cleanup, or how stale or incorrect history is controlled.
`track_user_message` | Track messages for repeat offenders; `get_user_profile` | Get user's moderation history; `get_high_risk_users` | List users with high violation rates
Use the tracking features only where appropriate, avoid unnecessary personal data, and check the package documentation for storage, retention, and deletion controls.