# Perspective API Alternative (Toxicity Detection)

> Perspective API Alternative (Toxicity Detection) is a paid MCP server for developer tools. Toxicity scores for text before an agent posts it, Perspective-compatible and LLM-free. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, CLI
- **Website:** https://apify.com/koyourmoon/perspective-api-alternative
- **Repository:** https://github.com/koyourmoon/perspective-api-alternative-mcp
- **MCP Registry name:** io.github.koyourmoon/perspective-api-alternative
- **Categories:** developer tools, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

Google is retiring its Perspective API on December 31, 2026, and this Actor on Apify copies its request and response format so moving over means changing the URL. It scores TOXICITY, SEVERE_TOXICITY, INSULT, PROFANITY, THREAT and IDENTITY_ATTACK from 0 to 1 using the open-source Detoxify model rather than an LLM, so the same text always scores the same. The README says English only, with a warning field on text that looks non-English.

The MCP server exposes a single tool, analyze_toxicity, taking 1 to 100 texts, an optional attribute list and a flag threshold (default 0.5 on toxicity). Long texts are chunked with overlap, but the author warns one insult in a very long polite text can score below 0.5, suggesting span annotations or a lower threshold.

Requests via API and MCP are held in memory only. Pricing on Apify starts at $0.35 per 1,000 text units; the README quotes $0.50 for the stdio package, and the first call after 60 idle seconds can take 10 to 30 seconds.

## Features

- **Perspective-compatible API:** Same request and response format and attribute names.
- **Six attributes:** Toxicity, severe toxicity, insult, profanity, threat and identity attack.
- **Deterministic:** Open-source Detoxify model, no LLM.
- **Batch scoring:** Up to 100 comments per call.
- **No stored text:** API and MCP requests are kept in memory only.

## Good for

- Screen an agent's reply before it posts
- Replace Perspective API in a comment system
- Moderate batches of user comments
- Flag toxic text above a custom threshold

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http perspective-api-alternative https://koyourmoon--perspective-api-alternative.apify.actor/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://koyourmoon--perspective-api-alternative.apify.actor/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "perspective-api-alternative": {
      "url": "https://koyourmoon--perspective-api-alternative.apify.actor/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "perspective-api-alternative": {
      "type": "http",
      "url": "https://koyourmoon--perspective-api-alternative.apify.actor/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "perspective-api-alternative": {
      "serverUrl": "https://koyourmoon--perspective-api-alternative.apify.actor/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "perspective-api-alternative": {
      "type": "http",
      "url": "https://koyourmoon--perspective-api-alternative.apify.actor/mcp"
    }
  }
}
```

## Tools

- `analyze_toxicity`: Scores 1 to 100 English texts for six toxicity attributes and flags those above a threshold.

## FAQ

### Does it support languages other than English?

No. The README says English only, with a warning on non-English text.

### Is the score repeatable?

Yes, because no LLM is used.

### Is my text stored?

The page says API and MCP requests are kept in memory and not logged.

### What does it cost?

From $0.35 per 1,000 text units on Apify.

### Is Perspective API Alternative (Toxicity Detection) free?

No. Perspective API Alternative (Toxicity Detection) is a paid product.

### How do I add Perspective API Alternative (Toxicity Detection) to Claude Code?

Run this command in your terminal: claude mcp add --transport http perspective-api-alternative https://koyourmoon--perspective-api-alternative.apify.actor/mcp

### What are the best alternatives to Perspective API Alternative (Toxicity Detection)?

The closest alternatives to Perspective API Alternative (Toxicity Detection) are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/perspective-api-alternative-toxicity-detection
