# Tanpin (oci · ghcr.io/willykeenan/tanpin:0.1.0)

Item-by-item inventory that reorders itself: per-SKU forecasts, purchase orders and ETAs.

- Trust score: 51/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-19

## Components

- oci · `ghcr.io/willykeenan/tanpin:0.1.0`: 51/100 (this document), [markdown](https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0.md), [page](https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/willykeenan/tanpin:0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-19.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 22 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1185 tokens (~74/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_purchase_order" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Tanpin MCP server?

Tanpin runs locally as a container image, launched with docker run --rm -i ghcr.io/willykeenan/tanpin:0.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add willykeenan-tanpin -- docker run --rm -i ghcr.io/willykeenan/tanpin:0.1.0
```

### Cursor

```json
{
  "mcpServers": {
    "willykeenan-tanpin": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/willykeenan/tanpin:0.1.0"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "willykeenan-tanpin": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/willykeenan/tanpin:0.1.0"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add willykeenan-tanpin -- docker run --rm -i ghcr.io/willykeenan/tanpin:0.1.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "willykeenan-tanpin": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/willykeenan/tanpin:0.1.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  willykeenan-tanpin:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/willykeenan/tanpin:0.1.0"]
```

### Netclaw

```json
{
  "McpServers": {
    "willykeenan-tanpin": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/willykeenan/tanpin:0.1.0"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "willykeenan-tanpin": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/willykeenan/tanpin:0.1.0"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 50, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 48, 0)

- [security regression] Provenance: unverified → fail

### 2026-10-12 (score 48, +1)

- [security regression] Provenance: fail → unverified

### 2026-10-10 (score 47, +2)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 47. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-06 (score 45, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 33. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 44, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (16)

### `get_overview` (~45 tokens)

Snapshot of the whole inventory: KPIs, items at/below reorder point, dead stock, open purchase orders with ETAs, and the last auto-management cycle. Start here.

### `list_products` (~50 tokens)

List products with live forecast and reorder math. Filter with low_stock or category.

Input parameters:

- `category` (string): Filter by category
- `low_stock` (boolean): Only items at/below their reorder point

### `get_product` (~47 tokens)

Full detail for one product by SKU (or internal id): forecast breakdown, safety stock, reorder point, EOQ, days of supply.

Input parameters:

- `sku` (string, required): SKU or product id

### `create_product` (~136 tokens)

Add a product to the catalog. supplier_name is matched or created automatically.

Input parameters:

- `category` (string): Category, e.g. beverage
- `current_stock` (number): Opening stock
- `lead_time_days` (number): Supplier lead time
- `min_order_qty` (number): Minimum order quantity
- `name` (string, required): Display name
- `pack_size` (number): Case/pack rounding
- `price` (number): Sell price per unit
- `sku` (string, required): Unique SKU
- `supplier_name` (string): Supplier name (created if new)
- `unit_cost` (number): Cost per unit

### `record_sale` (~60 tokens)

Record a sale — decrements stock, re-forecasts the item, and fires stock.low webhooks if it crosses its reorder point.

Input parameters:

- `qty` (number): Units sold (default 1)
- `sku` (string, required): SKU or product id

### `adjust_stock` (~58 tokens)

Manual stock adjustment (stocktake, shrinkage, damage). delta may be negative.

Input parameters:

- `delta` (number, required): Units to add (negative to remove)
- `reason` (string): Why
- `sku` (string, required): SKU or product id

### `get_reorder_recommendations` (~48 tokens)

What should be ordered RIGHT NOW — a dry run of the auto-ordering engine, grouped by supplier with quantities, costs, and minimum-order holds. Use before create_purchase_order.

### `create_purchase_order` (~104 tokens)

Create a purchase order. Either pass explicit lines (by SKU), or set from_recommendations=true to order exactly what the engine recommends for that supplier. Returns the PO with its delivery ETA.

Input parameters:

- `auto_send` (boolean): Immediately mark sent and email the supplier
- `from_recommendations` (boolean): Build lines from the reorder recommendations
- `lines` (array): Explicit lines [{sku, qty}]
- `supplier` (string, required): Supplier id or exact name

### `list_purchase_orders` (~35 tokens)

List purchase orders with statuses and delivery ETAs. status=open shows only in-flight orders.

Input parameters:

- `status` (string): Filter

### `send_purchase_order` (~44 tokens)

Send a draft PO — marks it sent and emails it to the supplier (SMTP if configured, local outbox otherwise).

Input parameters:

- `po_id` (string, required): Purchase order id

### `receive_purchase_order` (~38 tokens)

Receive a PO into stock (the delivery arrived). Writes receipt movements and updates stock levels.

Input parameters:

- `po_id` (string, required): Purchase order id

### `list_suppliers` (~28 tokens)

List suppliers with lead times, delivery windows, order cut-off hours, and minimum order values.

### `create_supplier` (~128 tokens)

Add a supplier. delivery_windows are the hours (0-23) deliveries arrive, e.g. "8,13,19" = three deliveries a day.

Input parameters:

- `cutoff_hour` (number): Order cut-off hour — later orders start lead time tomorrow
- `delivery_windows` (string): Comma-separated delivery hours, e.g. "8,13,19"
- `email` (string): Order email address
- `lead_time_days` (number): Days from order to delivery
- `min_order_value` (number): Minimum order value
- `name` (string, required): Supplier name

### `add_demand_hypothesis` (~148 tokens)

The forward-looking Tanpin Kanri move: tell the system about an upcoming event or weather change ("heatwave next week") and forecasts + automatic orders adjust immediately. multiplier 1.4 = +40% demand.

Input parameters:

- `category` (string): Apply to a whole category, e.g. beverage
- `days` (number): How many days it lasts (default 7)
- `multiplier` (number, required): Demand multiplier, e.g. 1.4 for +40%, 0.7 for -30%
- `note` (string, required): What is happening, e.g. "Local festival this weekend"
- `sku` (string): Or apply to one product

### `run_management_cycle` (~56 tokens)

Run one full auto-management cycle now: re-forecast every SKU, reclassify ABC, raise draft POs for anything below its reorder point, email them if auto-send is on, flag dead stock. Returns the cycle summary.

### `get_movements` (~51 tokens)

Stock movement audit trail (sales, receipts, adjustments), newest first.

Input parameters:

- `limit` (number): Max rows (default 50)
- `sku` (string): Filter to one product (SKU or id)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0#diagnostics

## Score history

- 2026-10-19: 51
- 2026-10-18: 51
- 2026-10-17: 50
- 2026-10-16: 50
- 2026-10-15: 49
- 2026-10-14: 49
- 2026-10-13: 48
- 2026-10-12: 48
- 2026-10-10: 47
- 2026-10-06: 45
- 2026-10-04: 44
- 2026-10-03: 44
- 2026-10-02: 43
- 2026-10-01: 43
- 2026-09-30: 42
- 2026-09-29: 42
- 2026-09-28: 41
- 2026-09-27: 41
- 2026-09-26: 41

## Common questions

### What is the Tanpin MCP server?

Tanpin is an MCP server listed in the public MCP registry as io.github.willykeenan/tanpin. Item-by-item inventory that reorders itself: per-SKU forecasts, purchase orders and ETAs. This page covers its container image (ghcr.io/willykeenan/tanpin:0.1.0).

### Is the Tanpin MCP server safe to use?

Tanpin scores 51 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Tanpin MCP server expose?

Tanpin exposes 16 tools: get_overview, list_products, get_product, create_product, record_sale, and 11 more. Their descriptions and schemas cost roughly 1,076 tokens of context every time the server is loaded.

### Is the Tanpin MCP server still maintained?

Tanpin is still listed as active in the MCP registry. We last reached this channel on 19 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Tanpin MCP server under?

Tanpin declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/willykeenan/tanpin
- Repository: https://github.com/willykeenan/tanpin
- Website: https://huggingface.co/spaces/willykeenan/tanpin
- Changelog RSS feed: https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0.xml
- Changelog JSON feed: https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0.json
- HTML version of this page: https://verifymcp.io/servers/willykeenan-tanpin/ghcr-io-willykeenan-tanpin-0-1-0