Name: Port OS Smart Home
Author: portpowered

Port OS Smart Home MCP

Control your Philips lights, Sonos speakers, Roborock vacuums and more with Port OS cloud.

Tool-list grade A Remote · Streamable HTTP OAuth 2.1 10 tools v1.0.1-metadata.1

No reviews yet by portpowered The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Control your Philips lights, Sonos speakers, Roborock vacuums and more with Port OS cloud.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http port-os-smart-home-mcp https://api.portoperatingsystem.com/mcp

# 2 — ask your agent for something these tools do
#   control, endpoint_manage, endpoint_query and 7 more

Port OS Smart Home costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

portpowered1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Control connected devices and services, retrieve results, and capture camera snapshots. Choose exactly one target: id for a specific endpoint/group, or query using the same field-first filter as endpoint_query. Query targeting can control all matching authorized devices in one durable request; it is not restricted to a named device or group. Port OS freezes every selected recipient once, across a

Parameter	Type	Required	Notes
correlationToken	string	no	Optional caller-provided correlation token. For PIN mutations, omission uses idempotencyKey as the operation token; use it with query-operation after an uncertain result.
id	string	no	Full Port OS endpoint ID (…/endpoints/…) from endpoint_query or group ID (…/endpoint-groups/…) from group_query.
idempotencyKey	string	yes	Stable unique key for this intended command. Reuse the same key after an uncertain response; a retry attaches to the same durable request for 24 hours.
message	string	yes	Full message ID copied from the target's messages: <capability-interface-namespace>/messages/<message-name>, with an @<version> suffix only when the listed ID has one.
payload	object	yes	JSON object matching the message payload schema. Use {} for messages without fields.
query		no	Field-first endpoint query, exactly as endpoint_query. Mutually exclusive with id and routeId; all authorized matches are frozen once, up to 100 recipients.
routeId	string	no	Optional provider route ID copied from the target routes. Reuse it for pause, resume and volume after playing through that provider. It must belong to id and advertise the requested message. Without i
waitForResult	boolean	no	Wait until the durable request reaches a final status. Result-returning commands wait for a correlated validated reply; response-less commands finish on provider delivery acknowledgment. Physical stat

Manage the names, types and registry entries of your devices and connected services. Send the complete name, type and enablement document for every metadata replacement, with etag from the read and a stable idempotencyKey. Choose one operation: RENAME, SET_TYPE, SET_ENABLEMENT, MERGE_INTO, or DELETE. Use endpoint_query first and copy the full endpoint ID. Rename and type changes are durable acros

Parameter	Type	Required	Notes
enablement	string	no	Complete replacement enablement, required with name and type on metadata writes.
endpointId	string	yes	Full endpoint ID from endpoint_query.
etag	string	yes	Current endpoint writable document etag from endpoint_query.
idempotencyKey	string	yes	Unique request key. Reuse it for retries of the same change for 24 hours.
mergeInto	string	no	Full target endpoint ID; only for MERGE_INTO.
name	string	no	Complete replacement name, required with type and enablement on metadata writes.
operation	string	yes	—
targetEtag	string	no	Current target etag, required for MERGE_INTO.
type	string	no	Complete replacement type, required with name and enablement on metadata writes.

Find connected devices and services, discover their controls, and read their state. Start with a focused name, room or category query; follow paginationContext.nextToken. Results include full IDs, device types, provider routes, capabilities and accepted message IDs. An endpoint is a device or connected service, including a filesystem or media library. Copy IDs verbatim into control. For a known d

Parameter	Type	Required	Notes
enablement	string	no	Filter by ENABLED (default), DISABLED, or * for both. This filter is preserved by pagination.
endpointId	string	no	Return one endpoint by its full Port OS identifier. Cannot be combined with other filters or pagination. Results advertise its declared command and outbound message IDs.
expand	array	no	Select observations to add to each device result, for example ["power", "connectivity"] or ["battery"]. Use capability names or full namespaces declared by the device. This reads attributes; it does n
forceDeviceAttributeQuery	boolean	no	Read selected attributes from devices instead of cache. Requires nonempty expand. Failed reads remain unavailable.
maxResults	integer	no	Maximum number of results (default 10, maximum 100).
nextToken	string	no	Opaque cursor returned by a previous endpoint_query call.
query	object	no	Optional field-first filter. Omit it to load full context; filter only when the account is large. Each key is a field or a combinator, and all keys of one object must match: {"name": {"like": "living"

Show Port OS devices with their supported controls. To show a device, always call this tool: the widget it opens is the device's UI, so never render a second card, map or controls for it; answer in a sentence or two. Uses the same selection, expansion and pagination arguments as endpoint_query. A single matching device opens its full view with now playing, transport, volume and other controls; s

Parameter	Type	Required	Notes
enablement	string	no	Filter by ENABLED (default), DISABLED, or * for both. This filter is preserved by pagination.
endpointId	string	no	Return one endpoint by its full Port OS identifier. Cannot be combined with other filters or pagination. Results advertise its declared command and outbound message IDs.
expand	array	no	Select observations to add to each device result, for example ["power", "connectivity"] or ["battery"]. Use capability names or full namespaces declared by the device. This reads attributes; it does n
forceDeviceAttributeQuery	boolean	no	Read selected attributes from devices instead of cache. Requires nonempty expand. Failed reads remain unavailable.
maxResults	integer	no	Maximum number of results (default 10, maximum 100).
nextToken	string	no	Opaque cursor returned by a previous endpoint_query call.
primary	string	no	The card to lead with, one of the device's card ids (shown as cardIds in the result), for example battery, fan, closure, thermostat, camera or remote; house-map for a vacuum's map or room picking (nev
query	object	no	Optional field-first filter. Omit it to load full context; filter only when the account is large. Each key is a field or a combinator, and all keys of one object must match: {"name": {"like": "living"

Organize rooms and device groups: create, rename, change members, enable, disable, merge or delete them. Create, delete, add/remove members, MOVE_MEMBER and rename default to providerSync BEST_EFFORT: send supported native group changes first, verify provider readback, then save Port OS intent. A provider failure falls back locally and is PARTIALLY_APPLIED. PORTOS_ONLY sends nothing; FAIL_ON_PROV

Parameter	Type	Required	Notes
idempotencyKey	string	no	Unique key for this intended change, at most 255 characters. Required unless validateOnly is true.
operations	array	yes	Compatible intended changes in one customer batch. Reuse each group's starting etag across its references; contradictory edits cannot be resolved by list order.
validateOnly	boolean	no	Validate and authorize the batch and report planned or unsupported provider dispatches without sending messages or writing.

Find rooms, floors, zones, homes and device groups, with their members and supported controls. Returns canonical IDs, names, etags, spatial roles, parent paths, children, member devices, controllers and providers. Call it without arguments first to load full context and follow every paginationContext.nextToken; filter with query only when the account is large. Controllers are the endpoints that

Parameter	Type	Required	Notes
enablement	string	no	Filter by ENABLED (default), DISABLED, or * for both. This filter is preserved by pagination; id reads ignore it.
expand	array	no	Select declared capabilities whose route observations to return, for example ["speaker", "media-player"]. Requires id. This adds state readings to the selected group; it does not expand group membersh
forceDeviceAttributeQuery	boolean	no	Requires id and nonempty expand; refresh provider state before returning route observations.
id	string	no	Return one group by its full group ID. Cannot be combined with query, maxResults or nextToken.
maxResults	integer	no	Maximum number of groups (default 25, maximum 100).
nextToken	string	no	Opaque cursor returned by a previous group_query call with the same query and maxResults.
query	object	no	Optional field-first filter. Omit it to load full context; filter only when the account is large. Each key is a field or a combinator, and all keys of one object must match: {"role": {"eq": "ROOM"}, "

Stop watching by cancelling one Port OS event subscription using its exact ID from subscription_list or subscription_inspect. Cancellation is idempotent. Select the intended subscription by name, source endpoint and catalog event; names are not cancellation keys. A stopped monitor requires a new subscription to watch again.

Parameter	Type	Required	Notes
id	string	yes	Exact subscription ID returned by subscription_list. Never use a display name or endpoint ID.
idempotencyKey	string	yes	Stable unique key for this write; reuse it only to retry the same request for 24 hours.
ifMatch	string	yes	Exact strong etag from subscription_inspect or subscription_list.

Inspect one Port OS event subscription by its exact ID returned by subscription_list. Returns its safe query, source endpoint, catalog name and lifecycle status. A retained active subscription establishes registration; it does not prove that any client has received or acted on a camera event.

Parameter	Type	Required	Notes
id	string	yes	Exact subscription ID returned by subscription_list. Never use a display name or endpoint ID.

Change only the display name of one Port OS event subscription by exact ID. Use a PLAIN name-value object. The event, endpoint, filter and destination are immutable; to change what is watched, establish a replacement monitor and cancel the old ID.

Parameter	Type	Required	Notes
id	string	yes	Exact subscription ID returned by subscription_list. Never use a display name or endpoint ID.
idempotencyKey	string	yes	Stable unique key for this write; reuse it only to retry the same request for 24 hours.
ifMatch	string	yes	Exact strong etag from subscription_inspect or subscription_list.
name	object	yes	—

Enumerate the user's Port OS event subscriptions, including their exact IDs, names, source endpoint, catalog event and status. For requests to stop watching a camera, list subscriptions and follow every nextCursor, select the intended monitor, then use subscription_cancel with its exact ID. Creating a monitor uses the host's events/subscribe capability after discovering supported camera events; t

Parameter	Type	Required	Notes
cursor	string	no	Opaque nextCursor from the preceding subscription_list page. Omit for the first page.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Port OS Smart Home or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.0.1-metadata.1 · scanned 28 Oct 2026

Graded from the tools this server lists, not from its source code.

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 score93

Findings0 threat · 1 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digestb0381cd12aa3da7949bf549ccfbf771f46c62510c8397e9229e9b09c23c00567

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

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.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

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. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
control	untrusted-inputexternal-sink	untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
endpoint_manage	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
endpoint_query	no tags
endpoint_show	no tags
group_manage	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
group_query	no tags
subscription_cancel	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
subscription_inspect	no tags
subscription_label_edit	state-write	state-write: declares readOnlyHint: false
subscription_list	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.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digestb0381cd12aa3da79

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.

Where are you running it?

Tool surface

Release history

Port OS Smart Home MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also