Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    MCP Security Gateway

    1

    Secure MCP interactions with guardrails, pattern matching, and output truncation. Block dangerous commands and protect sensitive systems.

    Free

    1 useSecurity scanned
    MCP Security Gateway

    MCP Security Gateway

    Example session with this skill installed

    I'm setting up an AI agent for our DevOps team that needs access to bash tools for server management. I'm worried about the agent accidentally running destructive commands. I need a security layer that will:

    1. Block dangerous commands like rm -rf, sudo, and kubectl delete
    2. Protect sensitive directories like /etc, /usr, and /var
    3. Log all tool executions for audit purposes
    4. Limit response sizes to prevent context overflow
    5. Work with our existing Claude Desktop setup

    Can you set this up quickly with Docker Compose?

    • Read your context and instructions
    • Compiled the mcp security gateway

    I'll set up the MCP Middleware Gateway with security guardrails:

    Configuration Applied

    ✅ Guardrails Enabled:

    • Blocked patterns: rm -rf, sudo , docker rm, kubectl delete
    • Protected paths: /etc, /usr, /var, /home, /root
    • Max response size: 2MB

    Docker Compose Setup

    git clone https://github.com/shouryasharan7-netizen/mcpmiddleware.git
    cd mcpmiddleware
    docker-compose up -d
    

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

    About this skill

    A production-ready Model Context Protocol (MCP) gateway that sits between your AI agents and tools. It provides a centralized reverse proxy with Redis-backed session affinity, ensuring multi-step agent workflows never lose state.

    Key Features Included

    Security & DLP: Deterministic payload inspection automatically redacts credentials, PII, and custom regex patterns before they reach the model. Access Control: Granular read/write RBAC enforcement so agents only access the tools they are authorized for. API Virtualization: Automatically wraps legacy REST (OpenAPI) and gRPC endpoints into MCP-compliant tools via reflection. Compliance Ready: Generates SHA-256 cryptographic execution fingerprints and exports OpenTelemetry (OTLP) traces. Deployment: Includes ready-to-run Kubernetes manifests (StatefulSets, headless services) and Dockerfiles.

    Requires Redis for production session handling. Adds a small latency overhead to tool calls. Response truncation is limited by the set MCP_MAX_RESPONSE_SIZE.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Network Access
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    Prompt-level instructions are often bypassed by jailbreaks; this gateway acts as a hard protocol-level firewall that kills dangerous commands like 'rm -rf' or unauthorized file access before they ever reach your shell.

    The gateway is built on the Model Context Protocol standard, making it compatible with any MCP-compliant client or server, including popular IDE extensions and custom agent frameworks.

    Setup is straightforward: you can deploy via Docker Compose for a production-ready stack with Redis, or use a simple Python configuration for local development and testing.

    While the proxy layer adds a necessary security check, the performance overhead is minimal, typically adding only single-digit milliseconds of latency to each tool call.

    The gateway includes built-in telemetry that logs execution latency, packet sizes, and user identities, providing a complete audit trail for compliance and monitoring purposes.

    You will receive the full middleware source code, deployment configurations for Docker and Python, and documentation for implementing OIDC authentication and custom guardrail logic.

    New in LLM Ops