Skip to content

CussCheck

by profanity-api.mike-tusa.workers.dev · remote · no sign-in to list tools · v0.3.0 · published by dev.workers.mike-tusa.profanity-api

English profanity filter: find and censor swear words, incl. obfuscations. Word list, not AI.

Changes · 1
CompareRegistry entry

1 tool: 1 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http profanity-api https://profanity-api.mike-tusa.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

1 tool

Changes things 1Claude Code: ask
  • check_profanityDetect English profanity in text (word list with leetspeak, look-alike letters, repeated letters, dotted/spaced letters and hidden characters handled) and return the matched terms,…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Detect English profanity in text (word list with leetspeak, look-alike letters, repeated letters, dotted/spaced letters and hidden characters handled) and return the matched terms, their positions (UTF-16 start/end in your text) and, unless censor is false, a censored copy of the same length. Common innocent words (Scunthorpe, cockpit, Shiite, cumin) are whitelisted; it does not understand context and is English only. Text up to 10240 UTF-8 bytes; it is not stored or logged. matches is capped at 50 here (match_count is the full total). Read-only. Same engine, keys and limits as POST /v1/check.

    Annotations the server declares

    • title: Check profanity
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http profanity-api https://profanity-api.mike-tusa.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__profanity-api__check_profanity"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as profanity-api. Review it before you use it.