InnerVault

OPNsense Guard

Stale Official MCP Registry, io.github.d3ltasecurity

Safety-first OPNsense firewall MCP: read-only by default, planned and auto-reverting writes.

Open the source (opens github.com) https://github.com/d3ltasecurity/opnsense-guard-mcp

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: OPNSENSE_API_KEY, OPNSENSE_API_SECRET. Use a key with the least access you can.

What it is

MCP servers from io.github.d3ltasecurity.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

pypi package (stdio)

opnsense-guard-mcp@0.1.1

From the server's entry in the official MCP Registry

Settings it asks for

  • OPNSENSE_URL required · Firewall base URL, e.g. https://firewall.example.internal
  • OPNSENSE_API_KEY secret required · API key of a least-privilege read user
  • OPNSENSE_API_SECRET secret required · API secret of the read user
  • OPNSENSE_CA_BUNDLE · CA file for a self-signed firewall certificate

Related

  1. OPNsense MCP Server

    MCP servers

    OPNsense MCP Server — 72 tools for DNS, Firewall, DHCP, ACME, Routing, VLANs & more

    Stale Official MCP Registry, io.github.itunified-io Updated 7 months ago 1 note

    @itunified.io/mcp-opnsense@2026.4.10-4
  2. Governed OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.

    Stale Official MCP Registry, io.github.AIops-tools Updated 2 days ago 1 note

    firewall-aiops@0.16.1
  3. GitHub MCP server

    MCP servers

    GitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.

    Hand-checked InnerVault (hand-checked), GitHub 34.3k ★MIT

    https://api.githubcopilot.com/mcp/
  4. Apify MCP server

    MCP servers

    Lets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.

    Hand-checked InnerVault (hand-checked), Apify 16.0k ★MIT

  5. guardana

    MCP servers

    Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

    Indexed GitHub, guardana 225 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/guardana/guardana.git
  6. Privacy guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and optional Spring Security tool authorization. Supports Presidio and JVM-local OpenNLP.

    Stale GitHub, ultramancode 22 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/ultramancode/spring-ai-privacy-guardrails.git