MCP server · Security
Perspective API Alternative MCP server
by koyourmoon
Check text for toxicity before your AI posts it, with six scores from 0 to 1.
This is a small helper that lets your AI check whether a piece of text sounds toxic before it goes out. It gives you six scores from 0 to 1, like insult, profanity and threat. It is handy if you use AI to write or post comments and want a quick safety check.
What is an MCP server? The 30-second version
On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to a toxicity checking service, so the AI can score text for you when you ask. You do not need to know how it works inside.
What this MCP server does
You ask your AI to check some text for toxicity. The AI sends the text to this helper. The helper passes the text to a toxicity service on Apify, which uses an open model called Detoxify. The service sends back six scores and a flagged value, and the helper gives them to your AI, which shows them to you in the chat.
What you can do with it
- Score one or many texts for toxicity
- See separate scores for insult, profanity, threat and identity attack
- Flag texts that go above a toxicity threshold you choose
- Check up to 100 texts in one request
- Get a warning when a text does not look like English
Try asking your AI
- “Check this comment for toxicity before I post it: You are an idiot.”
- “Score these five replies and tell me which ones are flagged at 0.7.”
- “Is this message insulting or threatening?”
- “Run a toxicity check on these customer reviews and list the flagged ones.”
What it gives back to you
You get back a list with one entry per text. Each entry has the original text, the scores from 0 to 1 for the attributes you asked for, and a flagged value that is true or false. If a text does not look like English, you also get a warning that the scores may not be reliable.
Before you start
What you need
- An Apify account and API token (a kind of password for apps; you get it in the Apify Console under Settings > API & Integrations)
- Python 3.9 or later, or Docker, if you run the server yourself
- An MCP client that can add servers, like the Claude desktop app
Good to know
Each check costs money through your Apify account (about $0.50 per 1,000 text units), and the scores only work well for English text.
Install it with your AI
Add Perspective API Alternative MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Perspective API Alternative MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.
Who it's for
People who use AI to write or post comments and want a quick, repeatable toxicity check before publishing.
