Skip to main content
Glama

forecast-mcp

一个MCP服务器(模型上下文协议),将三层需求预测和补货管道作为工具暴露出来。任何MCP客户端都可以调用它:Cursor、Claude Desktop、Claude Code、Google Antigravity、Windsurf,以及其他任何支持MCP的工具。 每个序列都使用Syntetos–Boylan统计量(ADI和CV²)进行分类,并路由到一个模型:

模式

典型序列

模型

冷启动

历史数据少于14天

观测需求的均值

间歇性/块状

稀疏、大部分为零的需求

TSB (statsforecast)

规律/不规则

连续日需求

AutoETS (statsforecast)

阈值:ADI = 1.32,CV² = 0.49(classification.py)。

工具

工具

用途

list_skus

加载数据集中的ID

classify_demand_pattern

模式 + 模型层级

forecast_series

路由后的预测范围

evaluate_forecast

留出回测(MASE)

recommend_replenishment

再订购点和订购数量

explain_forecast

路由理由

Related MCP server: shopify-forecast-mcp

数据

服务器在启动时在内存中生成一个包含25个SKU的合成面板(规律、不规则、间歇性、块状和冷启动)。无需外部数据集或API密钥。

要使用您自己的历史数据,请传递一个包含unique_idds(日期)、y(单位)的CSV文件:

python -m forecast_mcp.server --data examples/sample_demand.csv
# or
export FORECAST_MCP_DATA=/path/to/demand.csv

设置

python3 -m venv .venv
source .venv/bin/activate        # Windows: .venv\Scripts\activate
pip install -r requirements.txt
pip install -e ".[ui]"

运行

python -m forecast_mcp.server
python -m forecast_mcp.server --transport http --port 8765
python -m forecast_mcp.ui

HTTP健康检查:http://127.0.0.1:8765/health
MCP端点:http://127.0.0.1:8765/mcp
UI:http://127.0.0.1:7860

将MCP command指向此项目的.venv/bin/python

测试

pip install pytest
pytest tests/ -v

客户端配置

stdio(默认)和Streamable HTTP均受支持。示例配置位于examples/mcp/,以及.cursor/mcp.json.agents/mcp_config.json

{
  "mcpServers": {
    "forecast-mcp": {
      "command": "/absolute/path/to/forecast-mcp/.venv/bin/python",
      "args": ["-m", "forecast_mcp.server"]
    }
  }
}

HTTP:

{
  "mcpServers": {
    "forecast-mcp": {
      "url": "http://127.0.0.1:8765/mcp"
    }
  }
}

某些客户端使用serverUrl而不是url

扩展

  • 冷启动:将forecast_cold_start()中的均值回退替换为零样本基础模型(例如Chronos-Bolt)。

  • 每层额外候选:在evaluation.py中使用MASE评分。

  • 存储:将DataStore替换为ClickHouse、Postgres或DuckDB。

  • 具有外生特征的规律层:mlforecast + LightGBM。

布局

forecast-mcp/
├── src/forecast_mcp/
│   ├── server.py
│   ├── data.py
│   ├── classification.py
│   ├── forecasting.py
│   ├── evaluation.py
│   ├── replenishment.py
│   └── ui.py
├── scripts/
├── examples/
├── tests/
├── requirements.txt
└── pyproject.toml

Rohan Singh · github.com/RohanSingh02

Install Server
F
license - not found
A
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    A
    quality
    C
    maintenance
    Enables live read-only queries against SAP EWM CDS views and standalone inventory-math calculators (ABC/XYZ classification, safety stock, reorder point, slow-moving detection, demand forecasting).
    9

View all related MCP servers

Related MCP Connectors

  • Deterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even.

  • Neutral freight reference + validation layer for AI agents: ADR, HS, UN/LOCODE, freight math

  • Generate optimized work shift schedules from staffing demand, availability and fairness rules.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RohanSingh02/forecast-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server