Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    text moderation tool

    3

    Moderate toxic language, detect personal data leaks, and audit domain security configurations via MCP.

    Free

    5 usesSecurity scanned
    text moderation tool

    text moderation tool

    Example session with this skill installed

    Audit the following text for toxic language and personal info: 'Contact me at 555-0199, you idiot.'

    • Read your context and instructions
    • Compiled the text moderation tool

    The text contains toxic language (insult) and sensitive personal data (phone number). Moderation check failed. Please remove the offensive term and private contact information.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    User-generated content often contains toxic language, hate speech, or sensitive personal data that violates safety policies. Manually auditing text or misconfiguring moderation tools leads to security risks and inconsistent filtering.

    What it does

    • Identifies toxic language and hate speech within provided text strings.
    • Detects personal data leaks to ensure privacy compliance.
    • Manages session state and caching to optimize repeated moderation requests.
    • Provides structured error handling for missing parameters or API rate limits.
    • Audits domain and SSL configurations when triggered by specific infrastructure queries.

    Frameworks & tools

    Google Cloud NLP API, MCP (Model Context Protocol).

    Why this beats prompting it yourself

    Standard LLM prompting for moderation is prone to hallucinations and inconsistent safety thresholding. This skill connects to a specialized NLP moderation engine, manages stateful sessions, and handles infrastructure-specific audits like DNS and SSL verification that base models cannot perform reliably alone.

    Use cases

    • Audit domain configurations and SSL certificates for security compliance.
    • Moderate user-generated comments or messages for toxicity.
    • Scan text for accidental personal data exposure before storage.
    • Verify SPF and DMARC records during website configuration audits.

    Known limitations

    Requires a valid GOOGLE_CLOUD_NLP_API_KEY configured in your environment variables. The tool relies on session IDs for state management between calls.

    Requires GOOGLE_CLOUD_NLP_API_KEY environment variable. Specific infrastructure checks (SSL/DNS) are dependent on the underlying MCP server capabilities.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    5 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This tool combines Google Cloud NLP toxicity detection with infrastructure audit capabilities, allowing agents to filter hate speech, identify PII leaks, and verify SSL/DNS security configurations in one workflow.

    The skill is built on the Model Context Protocol (MCP), meaning it is compatible with any AI agent or platform that supports MCP connections, such as Claude Desktop or specialized IDE extensions.

    To function correctly, you must have a valid Google Cloud NLP API key and configure it as an environment variable (GOOGLE_CLOUD_NLP_API_KEY) within your agent's runtime environment.

    Unlike basic prompting, this tool utilizes a specialized NLP engine for consistent safety thresholding and includes stateful session management to handle repeated requests without losing context.

    Yes, the skill includes specialized tools to verify SPF, DMARC, and SSL certificates, making it ideal for developers who need to automate infrastructure security checks alongside content filtering.