Moderation API MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Moderation API MCP or direct API to detect unsafe content, route items for human review, manage authors, and apply moderation actions through natural language.

Moderation API logoModeration API
Api Key

Moderation API is a content safety service for detection, human review, author management, and moderation actions. Use it to keep user-generated content safer with clear workflows and audit-ready decisions.

11 Tools

Try Moderation API now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Moderation API
Try asking
TOOLS

Supported Tools

Every Moderation API action and event your agent gets out of the box.

Evaluate Content Without Storage

Evaluate content without retaining it or adding it to a review queue, and return policy findings and the recommended moderation action.

Execute Moderation Action

Apply a discovered moderation action to content items or authors.

Get Account and Quota

Return the connected Moderation API account, plan, current project, and current quota values.

Get Review Queue

Return metadata and item counts for a review queue by ID.

Get Wordlist

Return one wordlist and its current words by ID.

List Moderation Actions

List moderation actions available to the organization, optionally restricted to a review queue.

List Review Queue Items

List and filter one page of moderation items in a review queue.

List Wordlists

List the organization's wordlists and their identifiers.

Modify Wordlist Words

Add words to or remove words from an existing wordlist.

Set Review Queue Item Status

Mark a review queue item resolved or return it to pending.

Submit Content for Moderation

Evaluate content and allow Moderation API to retain it and add it to a review queue according to the project's configuration.

SETUP GUIDE

Connect Moderation API MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/openai @ai-sdk/mcp
Install the Composio SDK for Python or TypeScript
2

Initialize Client and Create Tool Router Session

typescript
import { Composio } from '@composio/core';

const composio = new Composio({ apiKey: 'your-api-key' });
const session = await composio.create('your-user-id');
console.log(`Tool Router session created: ${session.mcp.url}`);
Import and initialize the Composio client, then create a Tool Router session for Moderation API
3

Connect to AI Agent

typescript
import { openai } from '@ai-sdk/openai';
import { experimental_createMCPClient as createMCPClient } from '@ai-sdk/mcp';
import { generateText } from 'ai';

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: session.mcp.url,
    headers: {
      'x-api-key': 'your-composio-api-key',
    },
  },
});

const tools = await client.tools();
const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  messages: [{
    role: 'user',
    content: 'Review all flagged comments from today and summarize which ones need human escalation'
  }],
  maxSteps: 5,
});

console.log(`Agent: ${text}`);
Use the MCP server with your AI agent (Anthropic Claude or Mastra)
SETUP GUIDE

Connect Moderation API API Tool with your Agent

1

Install Composio

typescript
npm install @composio/openai
Install the Composio SDK
2

Initialize Composio and Create Tool Router Session

typescript
import OpenAI from 'openai';
import { Composio } from '@composio/core';
import { OpenAIResponsesProvider } from '@composio/openai';

const composio = new Composio({
  provider: new OpenAIResponsesProvider(),
});
const openai = new OpenAI({});
const session = await composio.create('your-user-id');
Import and initialize Composio client, then create a Tool Router session
3

Execute Moderation API Tools via Tool Router with Your Agent

typescript
const tools = session.tools;
const response = await openai.responses.create({
  model: 'gpt-4.1',
  tools: tools,
  input: [{
    role: 'user',
    content: 'Review all flagged comments from today and summarize which ones need human escalation'
  }],
});
const result = await composio.provider.handleToolCalls(
  'your-user-id',
  response.output
);
console.log(result);
Get tools from Tool Router session and execute Moderation API actions with your Agent

Why Use Composio?

AI Native Moderation API Integration

  • Supports both Moderation API MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable content review and action execution
  • Rich coverage for content detection, review queues, author management, and moderation decisions

Managed Auth

  • Secure API key handling without hard-coded credentials in your agent code
  • Central place to manage, scope, and revoke Moderation API access
  • Per user and per environment credentials so staging and production stay cleanly separated

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Clear tool schemas help agents understand when to flag content, escalate reviews, or take action
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Moderation API
  • Scoped, least privilege access to moderation resources and actions
  • Full audit trail of agent actions to support safety reviews, compliance, and appeals
FAQ

Frequently asked questions

Yes, Moderation API requires you to configure your own API key. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Start with Moderation API.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Moderation API tool your agent needs.Free to start.

Start building