How do I call this tool?

POST a JSON-RPC 2.29 tools/call request to https://mackorn.cn/ai/api/mcp.php with name "mackorn_distributor_eval". No installation is required.

Is the model based on published literature?

Yes. The particle-size and flow models are independently implemented from Whiten (1972) and Bond (1952); the implementation is MIT-licensed and auditable. Vendor data comes from MACKORN parameter tables. Every number carries its source; unknown values return null rather than an estimate.

mackorn_distributor_eval — Is this distributor reliable, and how much credit should we extend?

What it answers

按「能力/可靠/匹配」三维 17 项打分，区分公司代理与个人代理，输出分级 A/B/C/D、授信额度建议、风险清单与待核验项。

Input parameters

Parameter	Type	Description
`agent_type`	string	主体类型。个人主体风险显著更高，权重会自动上调、授信系数下调。
`country`	string	所在国家。
`scores`	object	各维度打分，取值 1 / 3 / 5（1=差，3=中，5=好）。未核验的维度请放入 missing，不要猜。
`missing`	array	尚未核验的维度名，用于标记未完成尽职调查的项目。未核验项不计入得分，但会拉低核验覆盖率；覆盖率低于60% 不得授信。

Worked example (real output, not a mock-up)

Run via: local plugin

Input:

{
  "agent_type": "公司",
  "scores": {
    "market_cover": 4,
    "sales_team": 3,
    "capital": 3,
    "years": 5,
    "credit_record": 5,
    "sanctions": 5
  }
}

Output (first fields):

Field	Value
`request.agent_type`	公司
`request.country`	null
`score`	29
`tier`	待核
`tier_note`	核验覆盖率不足 60%，不得授信
`verification_coverage_pct`	37
`veto_triggered`	[0 项]
`dimensions`	[17 项]
`credit_recommendation.tier`	待核
`credit_recommendation.max_open_account_units`	0
`credit_recommendation.basis`	分级待核基准 0 × 主体系数 1（公司）
`credit_recommendation.note`	不授信
`credit_recommendation.required_before_credit`	[4 项] ["工商与涉诉核验","第三方信用报告（D&B/Coface）","制裁名单筛查","至少 1 次成功试单"]
`risks`	[1 项] ["核验覆盖率仅 37% —— 未核验项不得作为决策依据"]
`pending_verification`	[11 项] ["技术服务能力","同类设备经验","仓储与备件库存能力","渠道网络"]
`next_actions`	[5 项] ["完成剩余 11 项核验：技术服务能力、同类设备经验、仓储与备件库存能力、渠道网络、主体类型（公司 vs 个人）等","官方核验：工商登记 + 涉诉 + 失信 + 制裁名单（全部免费）","第三方信用报告：D&B 或 Coface，出信用额度建议","实地或视频验仓：确认经营场所、库存、团队规模"]
`verification_channels`	[9 项]
`agent_type_note`	公司主体：可签约、可开票、可追责，标准权重

How to call it

POST a JSON-RPC 2.0 request to the public MCP endpoint — no installation, no API key:

curl -s https://mackorn.cn/ai/api/mcp.php \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"mackorn_distributor_eval","arguments":{"agent_type":"公司","scores":{"market_cover":4,"sales_team":3,"capital":3,"years":5,"credit_record":5,"sanctions":5}}}}'

Endpoint: https://mackorn.cn/ai/api/mcp.php · Registry: cn.mackorn/mackorn-cone-crusher · npm: mackorn-cone-crusher

Data sources and limits

Particle-size and flow models are independently implemented from published literature (Whiten 1972; Bond 1952). Vendor parameters come from MACKORN NH/NS tables. Every output carries assumptions[] and warnings[]; unknown values are returned as null, never estimated. Literature parameters must be calibrated against on-site sieve data before use in a formal proposal.

A hydraulic cone crusher is a secondary/tertiary machine: feed above roughly 350 mm is refused.