Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
groundhog.markets 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.
96/100
tool-list score
8
tools declared
remote
at its publisher
—
calls last 7d
What it does
groundhog.markets: free weather forecasts in one call, plus Kalshi and Polymarket market rules.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http groundhog-markets-mcp https://groundhog.markets/mcp
# 2 — ask your agent for something these tools do
# forecast, places, sources and 5 more
groundhog.markets costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GRAll 1 server
groundhog1 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 groundhog-markets-mcp https://groundhog.markets/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
8 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.
Daily high/low for any place from every free forecast: median, spread, rain, current obs and active alerts, with credits and the page URL. line ≈321 tok, week ≈566, table ≈1,567, series ≈1,564. Keep the credits and link the page when you repeat numbers. size=runs: one place, each source's newest runs by day with run_utc and fetched_at; NBM adds XND, P12, Q12. variable=rain: members' share of 0.01
| Parameter | Type | Required | Notes |
|---|---|---|---|
| place | yes | Slug, name, 'City, ST', 'City, Country', ICAO or 'lat,lon'. An array (up to 10) for line/week. | |
| date | string | no | today | tomorrow | +N (0-7) | YYYY-MM-DD, each place's local date. Default: today before 15:00 local, else tomorrow. |
| days | integer | no | week/table days (default 7) |
| size | string | no | default line; runs = each source's newest runs by day (trading fields) |
| format | string | no | line md, others tsv |
| units | string | no | default F in the US, else C; rain in inches with F, mm with C |
| hours | integer | no | series hours (72) |
| step | integer | no | series step hours (temp 3, rain 6) |
| include_6h | boolean | no | temp only: also count 6-hourly (~) days |
| all | boolean | no | table: also twin and stale rows |
| credits | string | no | — |
| runs | integer | no | size=runs: newest runs per source (1) |
| variable | string | no | temp (default) or rain |
| win | string | no | rain: lst = the climate day at a daily-rain settle station, cal = calendar day |
| stn | string | no | rain: a settle station of the place, e.g. KORD |
Find a place slug by name, City, ST, airport code or lat,lon; says full blend or grid only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | — |
| limit | integer | no | — |
Open sources groundhog uses: licence, latest run, age, status.
No parameter schema on file.
Weather markets in a place (Kalshi, Polymarket high/low/rain): settlement station and rule, the number so far under that rule, our value and the official result once settled, forecast daily max/min at the station. No prices. Needs place or family. line ≈520 tok, table ≈1,757; every city ≈36,291. With neither: the list of market cities.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| place | no | Slug, name, 'City, ST' or ICAO; an array for up to 10 places | |
| family | string | no | high | low | rain | all (default all); alone: every market city |
| date | string | no | today | tomorrow | yesterday | YYYY-MM-DD, each place's local date (default today) |
| size | string | no | line (default with place) | table (default without) |
| format | string | no | line md, table tsv |
| credits | string | no | — |
How often our settle value matched the venue's result, with every miss. No prices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | last N days (30) |
| venue | string | no | — |
| family | string | no | — |
| format | string | no | default tsv |
Search places by name, City, ST, airport code or lat,lon. Returns {results: [{id, title, url, text}]}; pass an id to fetch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
The 7-day forecast of a place id from search: {id, title, text, url, metadata}. Keep the credits and link the url when you repeat numbers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
As-issued history for backtests (no look-ahead): kind=daily (every source's daily hi/lo/rain per run at a place), nbm (NBM text columns: TXN, XND, P12, Q12; view=day = the books' day view) or obs (settlement truth: CLI, routine-METAR max/min). from/to (<= 366 days, 1 unit per 31 days); run=ISO | lead=N (+cycle=H: the run issued N days before) | asof=ISO (what was known then). Rows carry fetched_at
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | no | daily (default) | nbm | obs |
| place | string | no | slug, name or ICAO (kind=daily; nbm/obs: its station) |
| stn | string | no | ICAO (kind=nbm, obs) |
| from | string | yes | first target date YYYY-MM-DD |
| to | string | no | last target date (default from) |
| source | string | no | kind=daily: source ids, comma list (e.g. nbm,gfs,ifs) |
| prod | string | no | kind=nbm: nbe (default) | nbs |
| els | string | no | kind=nbm: elements, comma list (TXN,XND,P12,Q12,TMP) |
| view | string | no | kind=nbm: raw (default) | day |
| product | string | no | kind=obs |
| run | string | no | one run, YYYY-MM-DDTHH:MMZ |
| lead | integer | no | the run issued N UTC days before each date |
| cycle | integer | no | with lead: only runs at H UTC |
| asof | string | no | newest run fetched by this UTC time (no look-ahead) |
| format | string | no | tsv (default) | json |
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 groundhog.markets 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 96 / 100
Release 1.2.0 · 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 score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestb6df7567c2afadea1a68e4e27967f3883838af912c2b5f43833837feb5bc7db1
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| forecast | no tags | |
| places | no tags | |
| sources | no tags | |
| markets | no tags | |
| receipts | no tags | |
| search | untrusted-input | untrusted-input: keyword "fetch" |
| fetch | untrusted-input | untrusted-input: keyword "fetch" |
| history | 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 digestb6df7567c2afadea
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
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 1.2.0.
1.2.0
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 groundhog.markets 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.