Plumber Mcp

    1

    Stop a leaked secret or a hijacked workflow before it ships.

    $11

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    plumber-mcp

    Example session with this skill installed

    Scan the current repository for any leaked API keys or risky GitHub Action permissions in the workflows folder.

    • Read your context and instructions
    • Compiled the plumber-mcp

    I have completed a security audit of the repository using the Plumber MCP server. The scan identified one critical leak and one high-severity workflow risk.

    Security Audit Results

    SeverityRule IDFileLineFindingFix
    CRITICALleak/api-keysrc/config.js14Leaked OpenAI-style key (sk-...)Move secret to environment variable (.env).
    HIGHsec/job-permissions.github/workflows/deploy.yml12Job has no permissions: block or uses write-allSet least-privilege permissions on the job.

    Summary:

    • Score: 91.6/100
    • Grade: A
    • Files Scanned: 12
    • Issues Found: 2

    The repository contains a hardcoded API key in the configuration and a deployment workflow with overly broad permissions. While the grade is technically an 'A' based on the issue count, the critical leak requires immediate attention.

    Next steps

    1. Move the OpenAI key from src/config.js to a .env file and add .env to your .gitignore.
    2. Revoke the exposed API key immediately in the OpenAI dashboard, as it is now compromised.
    3. Add a permissions: contents: read block to the deploy job in your GitHub Actions workflow.

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

    About this skill

    Stop a leaked secret or a hijacked workflow before it ships. A real MCP server — not just instructions — that scans repos and GitHub Actions workflows for leaked secrets, dead code, and AI slop. 26 deterministic rules, plain-English fixes, no API keys, offline.

    Supports GitHub Actions only. Skips secret detection in test directories. Requires Node 18+. No SARIF or vulnerability database integration.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Requires

    @parasraju/plumber-mcp
    Node.js
    Plumber MCP
    Git
    cache.

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Environment Variables
    Listed5 days ago
    Updated3 days ago

    What's inside

    Frequently Asked Questions

    Plumber MCP runs locally via stdio and makes zero external API calls, ensuring your source code and sensitive credentials never leave your machine during a scan.

    Unlike AI models that may inconsistently flag issues, this skill uses 26 deterministic rules to provide instant, sub-second security audits without token costs or hallucinations.

    Plumber MCP is compatible with any environment that supports the Model Context Protocol (MCP), including Claude Code and Cursor.

    Yes, the tool includes specific checks for 'AI-elided' code (like '// ... rest of code' comments) and empty test assertions often generated by LLMs, ensuring your code is complete and functional.

    To prevent false positives, the scanner automatically ignores files located within test directories, as these often contain intentional mock credentials for testing purposes.

    New in Security