pfsense-mcp-server@1.1.0
CAUTION· not startedPublisher claims: "Security-focused local MCP server exposing strongly typed READ tools for pfSense." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- pfsense.local (its own)Also lab.invalid, pfrest.org, netgate.com, example.invalid — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable and talks to pfsense.local, its own; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTTP URL with a raw public IP address; HTTP URL with a raw public IP address; Image alt text carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
print(" Example: https://192.0.2.1", file=out)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.example="https://192.0.2.1",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.print(" Example: https://192.0.2.1", file=out)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Authorization path: the default profile has 0 WRITE tools and is not reachable; an explicit operator opt-in provisions the write_protected profile plus full TieFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct._USER_AGENT = "pfsense-mcp-server-pfrest-docs/1 (+https://github.com/night4me/pfsense-mcp-server)"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.example="https://192.0.2.1",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Generated by scripts/generate_trust_diagrams.py -- edit the node/edge data there and re-run it to regenerate this image (not a live Mermaid diagram: GitHub rendFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for pfsense-mcp-server@1.1.0 as of 2 h ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim night4me: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- URL using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.