Kuaidi100 launched China's first MCP-protocol-compatible logistics information service platform. The core API services of Kuaidi100's Baidiy
Nothing to run from here
Po Pilot 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
10
downloads a day
local
runs on your machine
402
downloads in 30d
What it does
Post-Stocky Shopify replenishment, MOQ Purchase Order generator, and 3-way invoice match MCP.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user po-pilot-mcp '--' npx -y po-pilot-mcp
# 2 — ask your agent for something these tools do
# calculate_replenishment_plan, build_supplier_purchase_orders, reconcile_po_three_way_match and 1 more
Po Pilot costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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 Po Pilot 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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user po-pilot-mcp '--' npx -y po-pilot-mcpReconnect, 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 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
4 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.
Replaces Shopify Stocky's retired forecasting brain. Computes margin-weighted ABC classes, stockout-adjusted daily sales velocity, demand + lead-time variability safety stock (SS = Z * sqrt(LT*sigma_d^2 + d^2*sigma_LT^2)), reorder points, inventory position (On-Hand + On-Order - Committed -…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skus | array | no | Structured SKU inventory + velocity rows. |
| inventory_csv | string | no | Raw CSV exported from Shopify Admin Products or merchant reorder spreadsheet. |
| supplier_rules | array | no | Optional supplier rules (e.g. from migrate_stocky_csv_snapshot) to apply vendor lead_time_days overrides. |
| use_live_shopify | boolean | no | Pull live variants and paid order velocity from configured Shopify Admin GraphQL API (Pro / License). |
| demo_mode | boolean | no | Run immediately against the built-in US Shopify merchant dataset (no API keys required). |
| service_level | yes | — | |
| review_period_days | integer | no | Days between purchasing review cycles (e.g., 7 for weekly, 14 for bi-weekly). |
| window_days | integer | no | Lookback window in days when parsing CSV or querying live Shopify orders. |
Turns SKU demand signals into ready-to-send Purchase Orders grouped by vendor. Enforces carton/case-pack multiples, per-SKU MOQs, supplier-level minimum units/USD thresholds (topping up A-class SKUs first), US import tariff + freight landed unit costs with margin-erosion alerts, and optional…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skus | array | no | Structured SKU inventory + velocity rows. |
| inventory_csv | string | no | Raw Shopify Products/Inventory CSV text. |
| supplier_rules | array | no | Per-vendor MOQ, minimum USD spend, import tariff %, freight USD, lead time override, payment terms, email, and ship-to location rules. |
| use_live_shopify | boolean | no | Pull live store SKUs and barcodes from Shopify Admin GraphQL (Pro / License). |
| demo_mode | boolean | no | Generate full multi-vendor POs using the built-in Austin, TX merchant demo dataset. |
| service_level | yes | — | |
| review_period_days | integer | no | Days of forward cover to buy beyond lead time. |
| po_prefix | string | no | Prefix for generated Purchase Order numbers. |
| max_cash_budget_usd | number | no | Optional Open-to-Buy (OTB) maximum landed cash spend ceiling in USD across all generated POs. Trims lowest-priority C/B cartons first while protecting CRITICAL A-class SKUs. |
| default_import_duty_pct | number | no | Fallback US import tariff / customs duty % when not specified on a vendor's supplier_rules entry. |
| min_gross_margin_pct | number | no | Minimum acceptable landed gross margin % before triggering margin_erosion_warning: true on a PO line. |
Deterministic Finance Ops 3-way match engine for wholesalers and Shopify merchants. Cross-examines approved Purchase Order lines, warehouse dock receiving counts (good vs damaged units), and billed supplier invoice lines to catch silent unit-price creep, short-shipments billed in full, unapproved…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| po_number | string | no | Purchase Order reference number. |
| vendor | string | no | Vendor or distributor name. |
| invoice_number | string | no | Supplier invoice number for QuickBooks/Xero Bill CSV export (defaults to INV-<po_number>). |
| invoice_date | string | no | Invoice date in YYYY-MM-DD format (defaults to today UTC). |
| due_date | string | no | Bill due date in YYYY-MM-DD format (defaults to Net 30 from invoice_date). |
| currency | string | no | 3-letter ISO currency code for QuickBooks/Xero export. |
| qbo_expense_account | string | no | QuickBooks Online expense/COGS account name (defaults to 'Cost of Goods Sold'). |
| xero_account_code | string | no | Xero chart-of-accounts code for inventory/COGS lines (defaults to '310'). |
| po_lines | array | no | Approved Purchase Order line items. |
| receiving_lines | array | no | Warehouse receiving counts per SKU. |
| invoice_lines | array | no | Billed lines extracted from the supplier PDF/CSV invoice. |
| invoice_extra_fees_usd | number | no | Freight, pallet, or handling charges billed on the invoice. |
| agreed_freight_cap_usd | number | no | Maximum freight/shipping charge agreed on the PO, if applicable. |
| demo_mode | boolean | no | Run a realistic 3-way match audit catching silent price creep, damaged units, and unapproved pallet fees. |
Shopify Stocky shut down on August 31, 2026 and never provided a Supplier Directory export. Paste a historical Stocky Purchase Orders CSV export (or pass demo_mode: true) and this tool reconstructs every supplier profile: actual observed lead-time average and standard deviation from…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| stocky_po_csv | string | no | Raw CSV content from Stocky Purchase Orders export. |
| demo_mode | boolean | no | Test supplier reconstruction using the built-in Stocky PO CSV fixture. |
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 Po Pilot 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 1.0.0 · scanned 28 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 score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest57bb19d08e74bfecea8af59ad772027c86e7bcc56b875ac20be7348b881c2b00
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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (4 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| calculate_replenishment_plan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| build_supplier_purchase_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| reconcile_po_three_way_match | no tags | |
| migrate_stocky_csv_snapshot | 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 digest57bb19d08e74bfec
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.0. Pin a release below and the command asks for exactly that one.
1.0.0
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 Po Pilot 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.