Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Z Zero 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
trust score
11
downloads a day
local
runs on your machine
702
downloads in 30d
What it does
Z-ZERO MCP Server — Secure JIT Virtual Card Payment tools for AI Agents (Claude, Cursor, AutoGPT) — Real Single-Use Virtual Cards, settled in USDC on Base
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'Z_ZERO_API_KEY=${Z_ZERO_API_KEY}' --transport stdio z-zero-mcp '--' npx -y z-zero-mcp-server
# 2 — ask your agent for something these tools do
# list_cards, check_balance, get_deposit_addresses and 11 more
It needs Z_ZERO_API_KEY: this reads it from your environment, so export it first.
Z Zero costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DGAll 1 server
dempty-glitch1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Z Zero as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads Z_ZERO_API_KEY (Passport Key (zk_live_...) from z-zero.xyz/dashboard/agents) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx Z_ZERO_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'Z_ZERO_API_KEY=${Z_ZERO_API_KEY}' --transport stdio z-zero-mcp '--' npx -y z-zero-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free 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: Z_ZERO_API_KEY — Passport Key (zk_live_...) from z-zero.xyz/dashboard/agents. 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
14 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.
List all available virtual card aliases and their balances. No sensitive data is returned.
No parameter schema on file.
Check spendable USD balance for a card alias. For active token limits, use list_cards instead.
No parameter schema on file.
Get your Base deposit address to top up your wallet with USDC (or any supported stablecoin on Base).
No parameter schema on file.
Request a single-use JIT virtual card ($1–$100) locked to one amount + merchant. ⚠️ Read mcp://resources/sop first. Only call once the FINAL total is visible — for physical goods that is AFTER shipping is submitted (use get_merchant_hints to navigate there). For digital goods with the price…
No parameter schema on file.
Get merchant navigation flow for a domain or platform key (e.g. '_platform_etsy'). Returns pre_steps (how to navigate checkout) and platform notes. Call BEFORE starting checkout to understand the multi-step flow.
No parameter schema on file.
UCP discovery + quote — creates an UNPAID draft checkout; no money moves; NOT a payment rail yet. Checks whether a merchant speaks UCP (Shopify-native agent commerce), lists its declared payment handlers, and — when variant_gid or query is given — creates a DRAFT checkout and returns the…
No parameter schema on file.
Execute a payment with a one-time token. TWO CALLS: call it first WITHOUT recheck — nothing is charged and it hands you what the owner actually asked for, locked when the card was issued; look at the page again, then call it a second time with recheck to pay or to pause. Then Z-Zero opens a…
No parameter schema on file.
Cancel unused token and refund instantly. Use when user cancels the purchase or to free up a card slot.
No parameter schema on file.
Pause and ask the user for approval before risky actions (price mismatch, large amount, unusual request).
No parameter schema on file.
Activate a new Passport Key instantly, no restart needed. Only call when user explicitly provides a key.
No parameter schema on file.
Check if Passport Key is configured. Shows prefix only, for debugging.
No parameter schema on file.
⚠️ MANDATORY: Read mcp://resources/sop first. Only use on PAYMENT pages where final total is visible. Auto-detects Web3 or Fiat and completes payment. For physical goods (Shopify, Etsy), get_merchant_hints first.
No parameter schema on file.
Report a checkout you could not complete. Pick the failure_class that best matches what you saw — this feeds Z-ZERO's self-healing loop (labeled failures become better merchant hints for the next run). If nothing fits, use 'unknown' and describe what happened in error_message.
No parameter schema on file.
Check where an order ENDED UP, and prove it. Returns TWO separate axes:
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 Z Zero 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 93 / 100
Release 1.10.2 · scanned 15 Oct 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 score93
Findings1 threat · 5 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest42f3bb5c66ed4f1d314b9a12b4d70dccaf6cf097b4bcfbeb412f238b44e8fdd8
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_cards | no tags | |
| check_balance | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_deposit_addresses | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| request_payment_token | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_merchant_hints | no tags | |
| ucp_probe_checkout | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| execute_payment | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (fetch(${ZZERO_API}/api/checkout-hints) at dist/index.js:99 |
| cancel_payment_token | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| request_human_approval | no tags | |
| set_api_key | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP POST (fetch(${ZZERO_API}/api/keys/rotate) at dist/index.js:1028 |
| show_api_key_status | no tags | |
| auto_pay_checkout | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST (fetch(${ZZERO_API}/api/wallet/transfer) at dist/index.js:1176, handler sends an HTTP POST (fetch(${ZZERO_API}/api/checkout-hints) at dist/index.js:99 |
| report_checkout_fail | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST (fetch(${ZZERO_API}/api/checkout-hints) at dist/index.js:99 |
| verify_receipt | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest42f3bb5c66ed4f1d
Scanned2026-10-15
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 1.10.2. Pin a release below and the command asks for exactly that one.
1.10.2
30 Sep 2026
latestNo release note was published with this version.
1.10.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Z Zero 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.