A TypeScript implementation of a simple MCP server that exposes datetime information to agentic systems and chat REPLs
Nothing to run from here
Card Mailer 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
6
tools declared
remote
at its publisher
—
calls last 7d
What it does
Print and mail 5x7 holiday and thank-you photo cards to a US address list. $2.49/card incl. postage.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http card-mailer-mcp https://cards.onmax.me/mcp/claude
# 2 — ask your agent for something these tools do
# import_address_list, fix_address, design_card and 3 more
Card Mailer costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ONAll 2 servers
onmax2 servers
2 categories
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 card-mailer-mcp https://cards.onmax.me/mcp/claudeReconnect, 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
6 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.
Use this when the user wants to mail printed cards to people at US postal addresses and gives the addresses as pasted text, a CSV, or an .xlsx spreadsheet. Reads names and addresses, checks each against USPS data, and saves them as a recipient list. Returns a list_id, how many rows are ready, and the problem for each row that needs fixing. Up to 300 recipients; pass list_id to append rows to an ex
| Parameter | Type | Required | Notes |
|---|---|---|---|
| addresses_text | string | no | Addresses as pasted text or CSV. One recipient per line ("Name, Street, City, ST ZIP") or a CSV with a header row. |
| address_file | object | no | A CSV or XLSX file the user attached. |
| list_id | string | no | Existing list to append to. |
Use this to correct or remove one recipient in a list from import_address_list, by row number. Given fields replace the stored values and omitted fields keep theirs; if the row's problem says it could not be read, pass name, line1, city, state and zip together. Re-checks the address with USPS data. remove: true takes the recipient out of the mailing. Rows in a list that belongs to a paid order can
| Parameter | Type | Required | Notes |
|---|---|---|---|
| list_id | string | yes | — |
| row | integer | yes | — |
| remove | boolean | no | Remove this recipient from the mailing. |
| name | string | no | — |
| line1 | string | no | Street address |
| line2 | string | no | Apartment, suite, unit |
| city | string | no | — |
| state | string | no | — |
| zip | string | no | — |
Use this to create or edit the printed 5x7 postcard: a greeting on the front over or under the photo, and a message and sign-off on the back. Pass the photo the user attached as photo, or a public https image URL as photo_url; the image is downloaded and stored on cards.onmax.me. Without a photo the front is the greeting on a solid color. Pass design_id to edit a design: given fields replace the o
| Parameter | Type | Required | Notes |
|---|---|---|---|
| design_id | string | no | — |
| photo | object | no | Photo the user attached for the front. |
| photo_url | string | no | Public https URL of the front photo. |
| remove_photo | boolean | no | — |
| style | string | no | classic (red), evergreen (green), winter (blue), minimal (white), thanks (warm, for thank-you cards). |
| greeting | string | no | Front headline, e.g. "Happy Holidays", "Merry Christmas", "Thank You". |
| message | string | no | Message printed on the back. |
| sign_off | string | no | Signature on the back, e.g. "Love, The Garcias". |
Use this when the user asks what mailing a card to an imported list costs or when it will arrive. Returns the price per card (First-Class postage included), the total for the ready recipients, the send date and the expected arrival window. For a card preview with the price, first create or edit it with design_card, then pass that exact design_id here. This shows the current saved front and back ab
| Parameter | Type | Required | Notes |
|---|---|---|---|
| list_id | string | yes | — |
| design_id | string/null | yes | Required preview choice. Use the exact design_id returned by design_card for a preview with price. Use null only for a price-only request without a design. Do not omit. |
| arrive_by | string | no | Date the cards should arrive by, YYYY-MM-DD. |
| send_date | string | no | Date to print and mail, YYYY-MM-DD. Default: the latest safe date for arrive_by, otherwise the earliest business day (today if it is one). |
Use this when the user has seen the card and the quote and says they want to order. Creates an unpaid order for the ready recipients in list_id with design_id and returns a link to cards.onmax.me, where the user reviews the recipients and pays. Nothing is printed, mailed or charged until the user pays on that page. Recipients that still need fixing are left out. Each call creates a separate order
| Parameter | Type | Required | Notes |
|---|---|---|---|
| list_id | string | yes | — |
| design_id | string | yes | — |
| send_date | string | no | Date to print and mail, YYYY-MM-DD. |
| arrive_by | string | no | — |
| sender | object | no | Return address (US). |
Use this when the user asks whether a Card Mailer order was paid, printed, mailed or delivered. Takes the mailing_id returned by create_mailing (also the last part of the order link). Returns the status, send date, expected arrival and per-recipient counts. Does not change the order or track other USPS mail.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mailing_id | string | yes | — |
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 Card Mailer 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 1.0.2 · scanned 1 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 · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest27dee8c2b8fedee0454c8b2db28dbf4a625341bcb59da4b1a05a103fe38d556c
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 |
|---|---|---|
| import_address_list | state-write | state-write: declares readOnlyHint: false |
| fix_address | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| design_card | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| quote_mailing | no tags | |
| create_mailing | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_mailing_status | 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 digest27dee8c2b8fedee0
Scanned2026-11-01
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 1.0.2.
1.0.2
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 Card Mailer 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.