# botx402

> Inventory reorder plans from SKU sales, stock and lead times. $19 a run, paid by card.

- name: io.botx402/server
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 100/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.botx402%2Fserver
- tools: https://api.protogrid.dev/v1/servers/io.botx402%2Fserver/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "botx402": {
      "type": "http",
      "url": "https://api.botx402.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-15d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 100/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 321 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 321 tokens to load them all
- tool set hash: 8bd610bc83da856ea0d238648af8f7e1
- tools last changed: 2026-10-17T08:50:21.015Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.botx402/server.svg)](https://protogrid.dev/servers/io.botx402/server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `start_inventory_reorder` removed
  - Start a paid Inventory Reorder Snapshot run ($19.00 per run). This tool never charges anyone; it returns a Stripe checkout link that a person opens and pays. It creates the checkout and returns the link with a receipt_id and access_token. Nothing runs until the person pays on Stripe's page. Show the user the link and the price and ask them to pay; then call get_run with the receipt_id and access_token. Results are also emailed to the address given. Takes the same JSON as validate_inventory_reorder_inputs ({"inputs": {...}, "email": "..."}); run validate_inventory_reorder_inputs first, since invalid inputs are rejected here too. Each call creates a new checkout, so do not retry a call that succeeded. Returns: A PDF report and a JSON plan: one row per SKU (status, order quantity, days of cover, cash tied up) plus summary totals. Turns a store's per-SKU sales history, stock on hand, open purchase orders and supplier lead times into a reorder plan: which SKUs to reorder now and how many units (rounded up to MOQ and case pack), which are out of stock or will run out before the next delivery could arrive, which are overstocked or not selling, how much cash is tied up in excess stock, and which SKUs earn the revenue (ABC tiers). It is rule-based and deterministic, computed only from the figures supplied. It is not a forecast: it does not model seasonality, trend or promotions, multiple locations, variant roll-ups, supplier price breaks or margin. It does not connect to Shopify or any other system; the data is sent inline. Inputs: an as_of date, an optional window_days (28 to 365, default 90) that units_sold covers, and 1 to 800 SKUs, each with sku, units_sold, on_hand, unit_price and unit_cost. lead_time_days is needed per SKU or in defaults. The whole request must stay under 200 KB.
- 2026-10-17 `validate_inventory_reorder_inputs` removed
  - Check inputs for Inventory Reorder Snapshot before asking a human to pay. Free; nothing is charged, stored or run. Takes exactly the JSON start_inventory_reorder takes: {"inputs": {...}}, plus "email" if you have it (checked too, optional here). Returns either valid (with a one-line summary of what will be analysed) or every problem found at once, each with its path (e.g. inputs.skus[2].unit_cost) and how to fix it. Fix them all, call again, then call start_inventory_reorder with the same JSON plus the buyer's email. Turns a store's per-SKU sales history, stock on hand, open purchase orders and supplier lead times into a reorder plan: which SKUs to reorder now and how many units (rounded up to MOQ and case pack), which are out of stock or will run out before the next delivery could arrive, which are overstocked or not selling, how much cash is tied up in excess stock, and which SKUs earn the revenue (ABC tiers). It is rule-based and deterministic, computed only from the figures supplied. It is not a forecast: it does not model seasonality, trend or promotions, multiple locations, variant roll-ups, supplier price breaks or margin. It does not connect to Shopify or any other system; the data is sent inline. Inputs: an as_of date, an optional window_days (28 to 365, default 90) that units_sold covers, and 1 to 800 SKUs, each with sku, units_sold, on_hand, unit_price and unit_cost. lead_time_days is needed per SKU or in defaults. The whole request must stay under 200 KB.

Full history: https://api.protogrid.dev/v1/servers/io.botx402%2Fserver/changes

## Remotes

- https://api.botx402.io/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `get_run`: Check a run started with a start_ tool and fetch its results. Needs the receipt_id AND the access_token that start_ returned: the token is the proof that the caller started the run, and without it nothing is returned. Status is awaiting_payment (the user has not paid yet), running, completed or failed. When completed, structuredContent.result is the bot's full JSON result, ready to act on, and pdf_url links the PDF report (presigned, expires after 7 days). Free and read-only; poll about once a minute.
- `list_bots`: List the bots this server can run: what each one does, its price per run, what a run returns, its input schema, and the names of its validate_ and start_ tools. Free and read-only.