Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Drex Agent Firewall

    1

    Policy enforcement for AI-agent actions before they reach supported consequential tools and systems.

    $59

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Drex Agent Firewall places policy evaluation and guarded execution between AI agents and supported consequential actions.

    Actions routed through supported firewall interfaces are normalized into structured action envelopes, evaluated through Drex where configured, checked against deterministic policy, and enforced before execution.

    What it can mediate

    Supported integrations include:

    • MCP tool execution
    • Shell commands
    • Filesystem operations
    • Git operations
    • GitHub actions
    • HTTP/network actions
    • Secret and credential handling on supported paths
    • Agent-action audit recording

    Policy outcomes can allow, constrain, escalate, abstain, or block actions according to the configured policy and supported execution path.

    Why use it

    Drex Agent Firewall is designed for developers running AI agents that can interact with consequential systems.

    Example uses include:

    • Blocking destructive shell commands
    • Protecting sensitive filesystem paths
    • Controlling repository writes
    • Restricting Git and GitHub operations
    • Controlling outbound HTTP/network activity
    • Preventing supported secret-exfiltration paths
    • Mediating MCP tool calls
    • Creating local audit records for guarded actions

    Integration model

    The firewall supports a stdio MCP proxy, a direct guarded MCP server, and library adapters for supported action classes.

    Actions routed through these supported interfaces can be evaluated and enforced before execution.

    Drex classification is optional where supported. Local replay operation does not require live Drex API access. Live Drex classification requires separately authorized Drex credentials and network access.

    Security boundary

    Drex Agent Firewall is an enforcement layer for supported integrated paths.

    It is not a replacement for operating-system permissions, containers, sandboxes, microVMs, credential systems, or full host isolation.

    Native actions that bypass the firewall's supported MCP or guarded adapter paths are outside its mediation boundary.

    Optional sandboxing is host-dependent and does not establish complete host mediation.

    Local SQLite/WAL audit records can be modified by a local process with equivalent operating-system permissions.

    BoundaryStatus
    MCP mediationPASS
    Supported adapter mediation (shell, filesystem, Git, GitHub, HTTP)PASS
    Native host mediationNOT SUPPORTED
    Sandbox containmentPARTIAL (host-dependent)
    Audit tamper resistancePARTIAL

    Requirements

    • Python 3.10+
    • Compatible MCP stdio client/server setup for MCP use
    • Appropriate OS/tool access for enabled adapters
    • Drex API credentials only if live Drex classification is enabled
    • Network access only for features that require it

    Release verification (v0.1.4)

    • Final shipped test suite: 225 passed
    • GitHub host-security CI: 225 passed, 0 skipped
    • OCI security suite: 34 passed
    • Local targeted host/security suite: 101 passed
    • MCP/adapter/policy targeted suite: 43 passed
    • MCP initialize and tools/list: PASS
    • Verified MCP canary: safe routed action ALLOW (executed once); destructive routed action BLOCK (executed zero times); audit records created
    • Commercial package: 157 files, no live credentials or private deployment data

    Test results describe the verified release build; they are not a guarantee against every possible bypass or vulnerability.

    License

    Drex Agent Firewall Commercial License (proprietary). Version 0.1.4 is not open source. Published by ELYRAON.

    • Only actions routed through supported MCP or guarded adapter paths are mediated.
    • Native execution paths outside those integrations may bypass the firewall.
    • Optional sandboxing is host-dependent and is not complete host isolation.
    • The stdio proxy supports one synchronous upstream server.
    • Some inventory/listing operations may be audited without policy filtering.
    • Local SQLite/WAL audit records are not tamper-proof against a process with equivalent host permissions.
    • Live Drex classification requires separately authorized API access.
    • Some adapter capabilities depend on host tools and permissions.

    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 1 month ago

    Requires

    Nace

    Permissions

    Terminal / Shell
    Write Files
    Network Access
    Environment Variables
    Read Files

    Allowed Hosts

    drex.nace.ai

    Permissions depend on which features you enable. - Read/Write Files: configuration, local SQLite audit storage, explicitly routed filesystem operations, and repository/workspace operations. - Environment Variables: provider and path configuration, optional Drex credentials, optional HTTP/API configuration. - Terminal / Shell: routed shell operations, Git operations, and launching the upstream MCP server process. - Network Access (conditional): live Drex classification, guarded HTTP actions, and GitHub/API operations where configured. Local replay mode does not require network access. - Repository access: only when Git/GitHub enforcement is used. - drex.nace.ai: optional hosted Drex classification service. Live Drex access requires separate authorization and credentials and is not included with this purchase.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    No. It enforces policy for actions routed through supported integrations. Optional sandboxing can add containment for supported launched workloads, but the firewall does not claim complete host isolation.

    No. Native actions that bypass supported MCP or guarded adapter paths are outside the firewall's mediation boundary.

    Not for every mode. Local replay can operate without live Drex access. Live Drex classification requires separately authorized credentials and network access.

    Supported integrations include MCP calls and adapters for shell, filesystem, Git, GitHub, and HTTP/network actions.

    No. Local SQLite/WAL audit records provide an audit trail, but a process with equivalent host permissions can modify local audit storage.

    New in Security