The request "profanity" with "what to use" is ambiguous: it could mean profanity detection, filtering, or a profanity-related tool. The most direct match is Unprofane, a profanity-checking API with an MCP server 3. Replicate's NSFW filter 5 is an image-content filter, not a text profanity checker, and the other listed products do not show profanity handling in their sources.
A question back: Do you mean detecting profanity in text (e.g. user comments, chat), or filtering NSFW content in images? Which language or platform will you use?
- 1
Unprofaneunprofane.comwebsite read, tools not yet checked
A profanity API with a documented first check, contexts, policies, lists and keys, reachable over HTTP, SDKs, or an MCP server 3.
official:MCP server · Unprofane
- 2
Replicatereplicate.comverified and signed
Its m1guelpf/nsfw-filter model runs any image through the Stable Diffusion content filter 15, which screens images for NSFW content rather than text profanity.
for agents: m1guelpf/nsfw-filter
Sources
- 3Documentation | Unprofane docsunprofane.com · read 2026-10-29
- 5Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 15m1guelpf/nsfw-filter: declares "m1guelpf/nsfw-filter" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
github-release · github-release verified and signed
Guides IA through releasing a new version of a GitHub library end-to-end. Handles SemVer versioning and Keep a Changelog formatting automatically.
· async-std website read, tools not yet checked
A Rust library for easy and understandable async programming
· Unprofane docs website read, tools not yet checked
How to call the Unprofane profanity API: a first check in two minutes, then contexts, policies, evasion tags, lists, keys, errors and the Perspective migration.
· aio-libs Aiobotocore website read, tools not yet checked
· aio-libs Aiohttp website read, tools not yet checked
m1guelpf/nsfw-filter · m1guelpf/nsfw-filter verified and signed
Run any image through the Stable Diffusion content filter
littletry/video-nsfw-filter · littletry/video-nsfw-filter verified and signed
Detect NSFW content in sampled video frames with adjustable sensitivity, per-frame scores, and optional screenshots.
· Context7 website read, tools not yet checked
Get the latest docs into Claude, Codex, Cursor and other agents. Context7 serves current, version-specific docs and code examples for any library.
pytorch · huggingface-hub verified and signed
· lxml website read, tools not yet checked
lxml - the most feature-rich and easy-to-use library for processing XML and HTML in the Python language
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.