Local MCP capabilities provider for Expo
Nothing to run from here
Checkbox 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
35
downloads a day
local
or remote
410
downloads in 30d
What it does
Auto-renewal law compliance (ROSCA, CA, NY, other states) for subscription checkout and emails
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'CHECKBOX_API_KEY=${CHECKBOX_API_KEY}' --transport stdio checkbox-mcp '--' npx -y @checkbox-site/mcp
# 2 — ask your agent for something these tools do
# complete_setup, get_task, answer_task and 13 more
It needs CHECKBOX_API_KEY: this reads it from your environment, so export it first. Remote: OAuth sign-in · Package: API key.
Checkbox costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CHAll 1 server
checkbox1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads CHECKBOX_API_KEY (Checkbox API key (ck_test_… or ck_live_…). Free at https://app.checkbox.site/sign-up) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx CHECKBOX_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'CHECKBOX_API_KEY=${CHECKBOX_API_KEY}' --transport stdio checkbox-mcp '--' npx -y @checkbox-site/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://app.checkbox.site/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http checkbox-mcp https://app.checkbox.site/mcpFree 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: CHECKBOX_API_KEY — Checkbox API key (ck_test_… or ck_live_…). Free at https://app.checkbox.site/sign-up. You set it 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
16 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.
Call once the setup checklist next_action is "done" (or nothing else can be done without the human). Marks the setup finished and emails the person who approved it "<agent> set up Checkbox for <domain>" with what was created, what is still open and a review link. Idempotent: the email is sent…
No parameter schema on file.
One task of the compliance plan with the full change to apply (unified-diff template with machine-applicable edits, copy, or Stripe params), where to apply it, the legal requirement, its last verification and next_action. Use it when the plan JSON was truncated or before applying a task.
No parameter schema on file.
For tasks with status "manual": record the HUMAN's answer to task.question. Ask the human first and pass their words; never answer on their behalf (answers are legal attestations stored in the evidence vault). answer is one of task.question.options; yes / no also work (= confirmed / needs_change).…
No parameter schema on file.
Re-fetches the registered policies, pre-checks the checkout, re-evaluates every law and queues a scan. Use it for the first check after setup, after deploying several changes, or when the plan looks stale. Waits up to wait seconds, then call get_compliance_plan.
No parameter schema on file.
Status of a verification from verify_task / verify_site: pending, passed or failed, expected vs observed per check, the diff and next_action. Pass wait (≤ 30 s) to wait for a pending one.
No parameter schema on file.
A synthetic test subscription with every step (checkout, acknowledgment email, reminders at each legal window, cancellation, confirmation): what was observed, check results, evidence ids and fixes. While running, next_action.type is "wait" (poll again in a minute or two). When finished, apply the…
No parameter schema on file.
The account's sites in the current mode (test keys see only test-mode sites), newest first, each with its compliance status label. Use it to find a site id.
No parameter schema on file.
Where a site stands: one status (Compliant, Needs a fix, Not set up yet, Not checked yet, Your call) and the to-do list: the compliance plan's ordered open tasks, as on the dashboard. Use it for "am I compliant?"; get_task gives each change.
No parameter schema on file.
Findings (one per legal check per site) ordered by urgency: failing first, then by severity, each with citations. Filter by site, status (fail, needs_review, pass, not_applicable) and state (open, acknowledged, resolved, accepted_risk). Default: every open finding of every status. Use get_finding…
No parameter schema on file.
One finding: what was observed, the legal requirements (citations), evidence references, and the concrete FIX for the site's platform — verified disclosure text plus a code snippet (Stripe Checkout params, Payment Link, Shopify Liquid or HTML). target overrides the detected platform. Apply the…
No parameter schema on file.
WRITE: queues a real-browser scan of the site's sign-up / checkout and cancellation flow (1-3 minutes). Confirm with the user before calling repeatedly; scans count against fair-use limits. In live mode the account must be activated (verified domain). Poll get_scan until completed, then…
No parameter schema on file.
A scan's status (queued → running → completed | failed), warnings, and once completed the evaluation it produced (the site status and to-do list update from it).
No parameter schema on file.
Bug, idea or question: what you tried, happened, expected. type review: only after the human said yes and saw the text; about Checkbox, not the site: no site names, URLs, quotes, secrets, customer data or claims the site broke a law. score 0-10 (would recommend); ≤5 phrases in liked, disliked,…
No parameter schema on file.
Changes to automatic-renewal law that Checkbox tracks (catalog changes, laws taking effect or sunsetting), newest first, each with its effect on this account's sites. Use it for "did anything change?" or before a launch in a new state.
No parameter schema on file.
Consent receipts newest first. Filter by site, customer_reference (find the receipt behind a disputed subscription or chargeback), checkout_session, binding (bound / unbound / server) or source. Use get_receipt for one receipt's full detail and integrity check.
No parameter schema on file.
Records that the merchant sent a due notice (ntd_…), optionally with the email provider's message id. Idempotent. Only call this after the email was actually sent: a send before the window opens is refused, and an overdue notice marked sent is recorded as late. For an overdue notice that was not…
No parameter schema on file.
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 Checkbox 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 5 Nov 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 digeste63f8088cbc2baa38055076d629830a9bb14a87265e215004c82de109bcf4b64
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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digeste63f8088cbc2baa3
Scanned2026-11-05
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 Checkbox 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.