Server providing Argo CD integration for MCP clients.
Nothing to run from here
OPNsense Guard is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
2
downloads a day
local
runs on your machine
90
downloads in 30d
What it does
Safety-first OPNsense firewall MCP: read-only by default, planned and auto-reverting writes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'OPNSENSE_URL=${OPNSENSE_URL}' --env 'OPNSENSE_API_KEY=${OPNSENSE_API_KEY}' --env 'OPNSENSE_API_SECRET=${OPNSENSE_API_SECRET}' --transport stdio opnsense-guard-mcp '--' uvx opnsense-guard-mcp
# 2 — ask your agent for something these tools do
# change_apply, change_confirm, change_rollback and 27 more
It needs OPNSENSE_URL, OPNSENSE_API_KEY, OPNSENSE_API_SECRET: this reads them from your environment, so export them first.
OPNsense Guard costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
D3All 1 server
d3ltasecurity1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts OPNsense Guard as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads OPNSENSE_URL (Firewall base URL, e.g. https://firewall.example.internal), OPNSENSE_API_KEY (API key of a least-privilege read user), OPNSENSE_API_SECRET (API secret of the read user) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx OPNSENSE_URL …, setx OPNSENSE_API_KEY …, setx OPNSENSE_API_SECRET … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'OPNSENSE_URL=${OPNSENSE_URL}' --env 'OPNSENSE_API_KEY=${OPNSENSE_API_KEY}' --env 'OPNSENSE_API_SECRET=${OPNSENSE_API_SECRET}' --transport stdio opnsense-guard-mcp '--' uvx opnsense-guard-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: OPNSENSE_URL — Firewall base URL, e.g. https://firewall.example.internal; OPNSENSE_API_KEY — API key of a least-privilege read user; OPNSENSE_API_SECRET — API secret of the read user. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
30 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
APPLY a plan to the firewall. This changes the live firewall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan_id | string | yes | id returned by rule_plan / alias_plan (valid 15 minutes). |
| user_confirmed | boolean | no | the user approved this exact diff in the chat. |
KEEP an applied change: stops its automatic revert.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| change_id | string | yes | — |
REVERT a change now (pending or confirmed).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| change_id | string | yes | — |
Recent changes: pending (with seconds left), confirmed, reverted, failed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | number of changes (1-100). |
One change with its before/after snapshots.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| change_id | string | yes | — |
What this server is allowed to change: mode, interfaces, networks, limits.
Takes no parameters.
Quick security review of the ruleset and IDS.
Takes no parameters.
Plan firewall filter rule changes. CHANGES NOTHING on the firewall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operations | array | yes | — |
Plan firewall alias changes. CHANGES NOTHING on the firewall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operations | array | yes | — |
Show a plan created in the last 15 minutes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan_id | string | yes | — |
The last audit log events (plans, refusals, and later: changes).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | number of events (1-200). |
OPNsense firmware version and pending updates (needs the System: Firmware privilege).
Takes no parameters.
Hostname, uptime, load, and general system information.
Takes no parameters.
Memory, swap, and disk utilisation of the firewall itself.
Takes no parameters.
All services OPNsense knows about and whether each is running.
Takes no parameters.
Health snapshot: system, services, IDS state.
Takes no parameters.
Whether the Suricata IDS/IPS service is running, stopped, or disabled.
Takes no parameters.
Suricata configuration: enabled, IPS mode, interfaces, active rulesets.
Takes no parameters.
Whether Suricata is producing alerts, from its eve.json file metadata.
Takes no parameters.
The firewall filter ruleset, one line per rule.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | optional text filter (interface, description, address). |
| limit | integer | no | maximum rules to return (1-1000). |
| detail | boolean | no | return the full OPNsense rows instead of one-line summaries. |
One filter rule by UUID, with all fields.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| uuid | string | yes | rule UUID as shown by firewall_rules. |
Firewall aliases and their contents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | optional text filter on alias name or description. |
| limit | integer | no | maximum aliases to return (1-1000). |
Recent firewall log entries (pass/block decisions).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | number of log lines to return (1-1000). |
| search | string | no | optional filter phrase (IP, port, interface, action). |
Active connection state table.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | number of states to return (1-1000). |
| search | string | no | optional filter on address or port. |
Recent entries from the OPNsense system log.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | number of lines to return (1-1000). |
All network interfaces with status, addresses, and link state.
Takes no parameters.
ARP table: IP to MAC mappings currently known to the firewall.
Takes no parameters.
The firewall's active routing table.
Takes no parameters.
Current DHCP leases across all backends (Kea, ISC dhcpd, dnsmasq).
Takes no parameters.
GET any allowlisted OPNsense API path.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | API path beginning with /api/, e.g. /api/core/firmware/info |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install OPNsense Guard or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.1.1 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest4342c2d46bfeac8f55998dd957f9d2e4696e15fc79e3388aca371daaf14a8cbd
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (30 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
4 of the 30 recovered tools are registered only when not policy.writable is false (src/opnsense_guard/tools/plan.py:129) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
26 tools are registered unconditionally · 4 more only when not policy.writable is false (src/opnsense_guard/tools/plan.py:129) — typically when a key or option is configured. All 30 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| change_apply | no tags | |
| change_confirm | no tags | |
| change_rollback | no tags | |
| change_list | no tags | |
| change_get | no tags | |
| policy_show | no tags | |
| security_audit | no tags | |
| rule_plan conditional | no tags | |
| alias_plan conditional | no tags | |
| plan_get conditional | no tags | |
| audit_tail conditional | no tags | |
| system_status | no tags | |
| system_information | no tags | |
| system_resources | no tags | |
| service_list | no tags | |
| posture_check | no tags | |
| suricata_status | no tags | |
| suricata_settings | no tags | |
| suricata_alert_status | no tags | |
| firewall_rules | no tags | |
| firewall_rule_get | no tags | |
| firewall_aliases | no tags | |
| firewall_log | no tags | |
| firewall_states | no tags | |
| system_log | no tags | |
| interfaces | no tags | |
| arp_table | no tags | |
| routing_table | no tags | |
| dhcp_leases | no tags | |
| raw_get | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest4342c2d46bfeac8f
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.1. Pin a release below and the command asks for exactly that one.
0.1.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish OPNsense Guard can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.