Integration

Google Perspective integration

Google Perspective Comment Analyzer: score a piece of text for toxicity and related attributes such as insult, threat, profanity and identity attack, so a moderation decision can be made before publishing it, and send a corrected score back when a human reviewer disagrees. Two calls, and the service is reached with a Google Cloud credential. Accepts either a Google Cloud API key, which is how Perspective is normally consumed, or an OAuth2 credential.

Connect Google Perspective How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Google Perspective.Built from the 2 Google Perspective tools below, on the connection you add once.

Common Google Perspective use cases

sending a moderator override back so the model learns from it
holding back a comment for review when its toxicity score is high
recording that a comment flagged as toxic was actually acceptable
ranking a moderation queue by how likely each item is to be abusive

What you can do with Google Perspective

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

analyze_commentAnalyze commentPOSTScores a comment for toxicity and related attributes.
suggest_comment_scoreSuggest comment scorePOSTSubmits a human corrected score for a comment.

Use Google Perspective from Claude Code, Cursor or Codex

Connect Google Perspective in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google Perspective operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Google Perspective

Create your workspace
Sign up free. Nothing to install.
Connect Google Perspective once
Add your Google Perspective connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Google Perspective integration FAQ

What can you do with the Google Perspective integration?

LiveContext exposes 2 operations on Google Perspective, covering comment. Common uses include sending a moderator override back so the model learns from it, holding back a comment for review when its toxicity score is high and recording that a comment flagged as toxic was actually acceptable.