Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
CitySignal AI 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.
93/100
tool-list score
23
tools declared
remote
at its publisher
—
calls last 7d
What it does
Live road, transit, weather, power and water signals for US cities, plus your own spots and routes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http citysignal-ai-mcp https://citysignalai.com/mcp
# 2 — ask your agent for something these tools do
# list_cities, city_now, city_near and 20 more
CitySignal AI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CIAll 1 server
citysignalai1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http citysignal-ai-mcp https://citysignalai.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
23 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.
The cities CitySignal covers, with their slug, timezone, center point, the official sources it reads, and status: live, or preview (still being checked, open to sign-ups, trackers not yet public). Call this when unsure which city slug to pass.
No parameter schema on file.
Live alerts in a city, deduplicated from official feeds (roads, transit, weather, power, water, construction) and placed by the app's own rule into four buckets: now (live and current), ongoing (live for more than two days, or unconfirmed), ahead (starts later, within 7 days, grouped by day) and recap (ended in the last 12 hours). Each item carries a stable signal_id. Use this for any 'what is goi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| category | string | no | Only this category: road, transit, weather, power, water, construction, emergency, film, sanitation, government_notice. Omit for all. |
| limit | integer | no | Max items per bucket (default 25). |
Alerts within a radius of a latitude and longitude in a city, nearest first, each with its distance in miles: live ones (bucket now, ongoing or ahead) and ones that ended in the last 12 hours (bucket recap, so 'was there anything here this afternoon' can be answered). Default radius 3 miles, max 25. Use when the person names a place, an address or 'near me' and you have coordinates. It does not ge
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| lat | number | yes | — |
| lon | number | yes | — |
| radius_mi | number | no | — |
| category | string | no | Only this category: road, transit, weather, power, water, construction, emergency, film, sanitation, government_notice. Omit for all. |
| limit | integer | no | Max items per bucket (default 25). |
Week-over-week memory for a city: counts by category for the last 7 days and the 7 before, a plain-language read of the week, measured insights, where it concentrated (areas and corridors), why an unusual week was unusual, and what a newsroom published about it. Use for 'how has this week been', 'is this normal', 'where do outages keep happening'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
Four weeks of what happened in a city, sorted by kind, for one category. roads (default): crashes, stalled vehicles, hazards and debris, closures, vehicle fires. power: outages by size (one home, small, neighborhood, large), planned outages, downed or sparking lines. transit: delays, canceled trips, reduced service, detours, stop and station changes, planned work. roadwork: lane, ramp and full roa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| category | string | no | roads (default), power, transit, roadwork or water. |
| hour_of_week | integer | no | 0 = Sunday midnight in the city's own time, 17 = Sunday 5 PM, 137 = Friday 5 PM. Omit for the current hour. |
Report mode: how every live CitySignal city is doing, in one call. The CitySignal Index for the last complete week (Sunday to Saturday): each city scored against its own typical week (Quiet, Typical, Busy, Heavy, with how many times typical), per category (roads, water, power, construction, transit), the biggest departure, week over week, plus what is live in each city right now. Use for reporters
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | summary (default): the storylines and one line per city, for a quick read. detailed: every city's categories too, for a reporter writing it up. trend: each city's recent weekly totals, oldest first, f |
Events, concerts and home games coming up in a city within the next N days (default 7, max 14), with venue area, ticket price range and a ticket link when listed, and expected local traffic impact when known. Each event carries placeholder_url, a CitySignal summary card (not a picture) you may link as a tappable markdown link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| days | integer | no | — |
| limit | integer | no | — |
Full detail for one signal by its signal_id (from any other tool): summary, place, area, corridor, timing, source link, confidence and whether a live camera check confirmed or contradicted it. When a real picture exists it carries picture_url, label and link (a ready markdown link), and the card comes back inline for you only: give the person the link and never say an image is shown. In apps that
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| signal_id | string | yes | — |
Road cameras within a radius of a latitude and longitude (default 1 mile, max 5), nearest first, each with a link to its current still and whether it has live video; plus the camera checks CitySignal ran on alerts there in the last N hours (default 24, max 72): what the camera showed and whether it matched the alert. CitySignal does not record video, so footage of a past moment exists only as a ch
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| lat | number | yes | — |
| lon | number | yes | — |
| radius_mi | number | no | — |
| hours | integer | no | — |
| limit | integer | no | Max cameras and max checks (default 10). |
Up to six CitySignal picture cards for incidents in a city, including ones that already cleared: the frame a camera check kept, or a live view while the incident is still going. Each card has a headline, time, city, and a Cleared / Earlier today tag when it's over. Incidents with no picture are left out. Images in this tool's result are visible to the assistant only, not to the person. To show a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | no | City slug. One of: atlanta, nashville, charlotte, dallas, austin, seattle, chicago, san-francisco, raleigh-durham, houston, greensboro, birmingham, pensacola, louisville, san-jose, memphis, knoxville, |
| hours | integer | no | How far back, in hours (default 12). |
The connected CitySignal account: a stable opaque id and display name. Call this to confirm which account is linked before reading personal tools.
No parameter schema on file.
The connected person's own Now / Ongoing / Ahead / Recap: live signals that touch their saved spots and routes, in the same buckets the app shows, plus today's calendar line. Use for 'anything I should know today', 'what's near my places', 'is my area affected'. Needs a connected account.
No parameter schema on file.
Today's written brief for the connected person: top alerts, citywide items, what is near their spots with why it matters and a recommended action, events, what is ongoing, what came and went since the last brief. Use when they ask for their briefing or a summary of their day. Needs a connected account.
No parameter schema on file.
Each of the connected person's saved routes with its current state (Clear, Minor delay, Expect delays, Consider another route) and what changes how the road drives on its corridor now and ahead: crashes, lane closures, roadwork, weather over the route's counties, and event crowds around the trip time. Power, water and other at-a-place notices are NOT route delays; they belong to the person's spots
No parameter schema on file.
Errands on the connected person's list that fit a trip they already make today, with the store, the detour in minutes, why that store, and a price line when one is known. Use for 'what can I pick up on the way', 'any errands I can do today'. Needs a connected account.
No parameter schema on file.
The connected person's shopping list as Scout priced it at their home Kroger: each item with product, size, price and whether it is on sale, plus the running total. Non-private lists include a revocable share link that expires after seven days. Use for 'what's on my list', 'how much will groceries be', 'is anything on sale'. Needs a connected account.
No parameter schema on file.
The connected person's saved spots (name, kind, part of town, alert radius) and routes (name, from, to, schedule). Use to understand what 'home', 'work' or 'my commute' refer to before answering about them. Addresses are not included. Needs a connected account.
No parameter schema on file.
Adds one errand to the connected person's own list, in their words ('milk and eggs', 'pick up lotion at the pharmacy'), the way the app, Siri and a text to Scout do: Scout reads the store kind from the words and fits the errand into a drive they already make. Optional 'by': a day word (today, tomorrow, Friday) or a date (YYYY-MM-DD). Returns the item as the list shows it, a confirmation line, and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | What they need, in their words. A store named after 'at' or 'from' is kept and honoured. |
| by | string | no | A day word (today, tomorrow, Friday, next Monday) or an ISO date. Omit when they named no day. |
Saves a spot (a place that matters to the connected person, where Scout looks out for them) at an address they typed, with a kind: home, work, school, church, gym or other, and an optional name. The address must resolve to one confident, house-level match in their home city; when it does not, nothing is saved and the result lists the top suggestions with their lat and lon. Then ask the person whic
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | The street address or place name they typed. |
| kind | string | yes | home, work, school, church, gym or other. |
| name | string | no | A nickname. Defaults to the kind (Home, Work, School, Church, Gym); required for other. |
| lat | number | no | Only from a suggestion this tool returned, to confirm it. |
| lon | number | no | Only from a suggestion this tool returned, to confirm it. |
Scout's detour offers on the connected person's drives today, as the Scout page shows them: the streak line (how many drives or weeks straight home), the offer (worth it: an event they marked interest in, near a drive, as a stop; dodge it: a big crowd a drive passes, with the way around), the DETOUR-XXX code and what the code opens. The route's own state never changes because of an event. Use for
No parameter schema on file.
Resolves a DETOUR-XXX code for the connected person: which drive it is on, the event, whether it is worth it (a stop) or dodge it (a way around), the streak and offer lines, and the link that opens it. Codes are per person and per day; a code that has passed says so. Use when the person says or pastes a code. Needs a connected account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | The code, like DETOUR-KQM. |
Open errands and list items of people in the connected person's Circle, for people who turned on assistant access for them, with how long each has waited and whether it was already asked of or accepted by the connected person. When an errand lists what it is for, 'items' names them (a 'Groceries' errand with items oat milk, eggs, paper towels): name those items in the answer. An empty 'items' mean
| Parameter | Type | Required | Notes |
|---|---|---|---|
| person | string | no | First name to narrow to one person. |
| category | string | no | A kind of errand or a word from it: grocery, pharmacy, returns, milk. |
Trips people in the connected person's Circle already plan today or tomorrow that fit an errand: a store run someone's item could ride along on, a return or post office stop, a trip they both make. Returns the person's first name, the trip label, an approximate time only if they share times, the kind of store, and which of the connected person's items could ride along. Never a location. Use for 'i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | A store kind or word: pharmacy, grocery, Target, post office. |
| day | string | no | — |
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install CitySignal AI 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: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 21 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 · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest35db1813c732ef2159e5e8444ed927975d9fd7ef86425773b7dafccedbfb9196
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 |
|---|---|---|
| list_cities | no tags | |
| city_now | no tags | |
| city_near | no tags | |
| city_week | no tags | |
| city_incidents | no tags | |
| cities_report | no tags | |
| city_events | no tags | |
| get_signal | no tags | |
| city_cameras | no tags | |
| city_pictures | no tags | |
| get_profile | no tags | |
| my_day | no tags | |
| my_brief | no tags | |
| my_routes_now | no tags | |
| my_along_the_way | no tags | |
| my_list | no tags | |
| my_spots_and_routes | no tags | |
| add_errand | state-write | state-write: declares readOnlyHint: false |
| save_spot | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| my_detours | no tags | |
| get_detour | no tags | |
| circle_needs | no tags | |
| circle_along_the_way | 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 digest35db1813c732ef21
Scanned2026-10-21
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
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 CitySignal AI 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.