CussCheck is an MCP server published by dev.workers.mike-tusa.profanity-api, hosted at profanity-api.mike-tusa.workers.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 1 tool, including check_profanity.
English profanity filter: find and censor swear words, incl. obfuscations. Word list, not AI.
29 connections through 4 shared values. Tap any node.
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.
| Parameter | Type | Description |
|---|---|---|
| deny | array | Extra words to flag on word boundaries, e.g. ["jerk"]. |
| text * | string | The text to check, at most 10240 UTF-8 bytes. |
| allow | array | Words never to flag, e.g. ["hell", "damn"]. Allow wins over deny. |
| censor |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
| boolean |
| Return a censored copy (default true). |
{
"name": "check_profanity",
"title": "Find and censor English swear words",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"text"
],
"properties": {
"deny": {
"type": "array",
"items": {
"type": "string",
"maxLength": 40,
"minLength": 1
},
"maxItems": 50,
"description": "Extra words to flag on word boundaries, e.g. [\"jerk\"]."
},
"text": {
"type": "string",
"maxLength": 10240,
"description": "The text to check, at most 10240 UTF-8 bytes."
},
"allow": {
"type": "array",
"items": {
"type": "string",
"maxLength": 40,
"minLength": 1
},
"maxItems": 50,
"description": "Words never to flag, e.g. [\"hell\", \"damn\"]. Allow wins over deny."
},
"censor": {
"type": "boolean",
"description": "Return a censored copy (default true)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"has_profanity",
"match_count",
"terms",
"matches"
],
"properties": {
"terms": {
"type": "array",
"items": {
"type": "string"
}
},
"engine": {
"type": "string"
},
"matches": {
"type": "array",
"items": {
"type": "object",
"required": [
"term",
"start",
"end"
],
"properties": {
"end": {
"type": "integer"
},
"term": {
"type": "string"
},
"match": {
"type": "string"
},
"start": {
"type": "integer"
},
"source": {
"type": "string"
},
"obfuscated": {
"type": "boolean"
}
}
},
"maxItems": 50,
"description": "Matches in text order, at most 50 here (see match_count for the total). start/end are UTF-16 indices into your text."
},
"version": {
"type": "string"
},
"censored": {
"type": "string",
"description": "Your text with each match replaced by asterisks (same length). Omitted when censor is false."
},
"truncated": {
"type": "boolean",
"description": "True when matches lists fewer than match_count (over 50 here, or the API's own cap)."
},
"text_bytes": {
"type": "integer"
},
"match_count": {
"type": "integer",
"description": "Total number of matches in the text (not capped)."
},
"has_profanity": {
"type": "boolean"
},
"matches_returned": {
"type": "integer"
}
}
},
"annotations": {
"title": "Check profanity",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}CussCheck finds English swear words in text and returns their positions and a censored copy. It is a word-list filter (obscenity englishDataset) with leetspeak, look-alike character, repeated-letter, dotted/spaced-letter and hidden-character handling; it is not AI moderation and does not understand context. Use check_profanity with "text" (at most 10240 UTF-8 bytes). Optional "allow" and "deny" word lists (up to 50 words each). Positions are UTF-16 indices into your original text (start inclusive, end exclusive). The text is checked in memory and never stored or logged. Anonymous use: about 10 checks per minute and 200 per day per IP. A free API key (POST /v1/keys) gives about 60 per minute and 1000 per day; send it as X-Api-Key or "Authorization: Bearer pf_...". Each check_profanity call counts as one check.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.