Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
CarrierVet 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
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
Vet US motor carriers by USDOT or MC number: PASS/REVIEW/FAIL verdict, authority, insurance, OOS.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http carriervet-mcp https://carriervet.dev/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# lookup_carrier, get_risk, get_receipt and 7 more
It needs AUTHORIZATION (Bearer <your CarrierVet API key>. Free key (100 lookups/month, no card): https://carriervet.dev/#signup): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
CarrierVet costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CAAll 1 server
carriervet1 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 Code reads AUTHORIZATION (Bearer <your CarrierVet API key>. Free key (100 lookups/month, no card): https://carriervet.dev/#signup) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http carriervet-mcp https://carriervet.dev/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, 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 — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer <your CarrierVet API key>. Free key (100 lookups/month, no card): https://carriervet.dev/#signup. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
10 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.
Get a US motor carrier's FMCSA profile by USDOT number or MC/FF/MX docket number: legal name, operating authority status and age, insurance on file, out-of-service status, fleet size, address and contact. Returns an overall verdict (PASS, REVIEW or FAIL) with verdict_reasons, based on the PASS/FLAG/FAIL checks for authority, insurance, out-of-service, USDOT operating status and FMCSA safety rating
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dot | string | no | USDOT number, 1-8 digits, e.g. "1234567" |
| mc | string | no | MC, FF or MX docket number, e.g. "MC123456" or "123456" |
Get a 0-100 risk score for a carrier by USDOT number or MC/FF/MX docket number, with reason codes (e.g. insurance_lapsed, authority_under_90_days, shared_phone, multiple_contact_changes). Levels: low 0-24, elevated 25-49, high 50-74, severe 75-100. Hard failures (revoked, inactive or missing authority, out-of-service, lapsed or missing insurance, inactive USDOT number, not allowed to operate, Unsa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dot | string | no | USDOT number, 1-8 digits, e.g. "1234567" |
| mc | string | no | MC, FF or MX docket number, e.g. "MC123456" or "123456" |
Fetch the saved copy of an earlier lookup by its receipt_id: the time it was made, the endpoint, the identifier, and the exact response CarrierVet returned, with its SHA-256. Any API key on the account that made the lookup can read it. Receipts are saved a few seconds after the lookup. Free; does not cost a lookup.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| receipt_id | string | yes | receipt_id from an earlier response, e.g. rcpt_0123abcd... |
List changes CarrierVet detected in a carrier's FMCSA record (address, phone, email, authority, insurance, out-of-service), newest first, plus fmcsa_history: dated changes from FMCSA's daily files and census, each with the date FMCSA recorded it, the date CarrierVet saw it, and the before and after values. History starts on the date CarrierVet began recording, so older changes are not included. Re
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dot | string | yes | USDOT number, 1-8 digits, e.g. "1234567" |
Find carriers already stored by CarrierVet whose legal or DBA name contains the given text (max 25). Prefer lookup_carrier when you have a USDOT or MC number. Costs 1 lookup.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Company name or part of it |
Look up to 500 USDOT or MC numbers in one call from stored snapshots (Pro and Business plans). Each found result includes the same verdict, verdict_reasons and verdict_basis as lookup_carrier. Costs 1 lookup per unique identifier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| identifiers | array | yes | USDOT numbers and/or MC numbers like "MC123456" |
Show this API key's plan, lookups used and remaining this UTC month, monitor count and rate limit. Free; does not cost a lookup.
No parameter schema on file.
List carriers on this account's watchlist (monitors) with alert email, webhook and last delivery status.
No parameter schema on file.
Watch a carrier (paid plans) and get an email and/or signed webhook (Pro+) when its FMCSA record changes. The carrier must have been looked up at least once. Provide alert_email, webhook_url, or both.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dot | string | yes | USDOT number, 1-8 digits, e.g. "1234567" |
| alert_email | string | no | — |
| webhook_url | string | no | HTTPS URL (Pro and Business) |
Stop watching a carrier on this account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dot | string | yes | USDOT number, 1-8 digits, e.g. "1234567" |
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 CarrierVet 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 1.4.1 · scanned 3 Nov 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 · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest1f757e2ce25960c1282955315052f895b326d40887fd88c84a4b53104d886555
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 |
|---|---|---|
| lookup_carrier | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_risk | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_receipt | untrusted-input | untrusted-input: keyword "fetch" |
| get_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_carriers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| batch_lookup | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_usage | no tags | |
| list_watchlist | no tags | |
| add_to_watchlist | external-sinkstate-write | external-sink: keyword "webhook", parameter "webhook"; state-write: declares readOnlyHint: false |
| remove_from_watchlist | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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 digest1f757e2ce25960c1
Scanned2026-11-03
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 1.4.1.
1.4.1
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 CarrierVet 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.