Security-focused local MCP server exposing strongly typed READ tools for pfSense.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pfsense-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# pfsense-mcp-server <!-- Rendered from assets/brand/logo-lockup.svg -- see that file to edit the brand asset source. An absolute raw.githubusercontent.com URL is required, not a repository-relative path: this README's long_description is also embedded verbatim into the published PyPI package, which has no accompanying file tree to resolve a relative path against -- see docs/adr/ADR-034-mermaid-pypi-compatibility.md, which hit exactly this bug for the two diagram images below and established this project's one safe pattern (plain Markdown image syntax, absolute `main`-branch raw URL) that this hero image and both diagrams now all follow identically. -->  [](https://github.com/night4me/pfsense-mcp-server/actions/workflows/ci.yml) [](https://github.com/night4me/pfsense-mcp-server/actions/workflows/codeql.yml) [](https://pypi.org/project/pfsense-mcp-server/)  [](https://github.com/night4me/pfsense-mcp-server/blob/main/LICENSE)  **Safe, least-privilege pfSense access for AI assistants.** [MCP](https://modelcontextprotocol.io/) server that gives an AI assistant strongly typed, read-only visibility into one pfSense appliance — system, network, firewall, DHCP, DNS, VPN, certificates, and diagnostics — without raw shell access, an unaudited scripting surface, or any way to change the appliance by accident. I built …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.