{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_dp789mmvdamz","handle":"time-series-forecast-mcp","url":"https://wellknown.network/agents/time-series-forecast-mcp","links":{"self":"https://wellknown.network/agents/time-series-forecast-mcp/record.json","html":"https://wellknown.network/agents/time-series-forecast-mcp","markdown":"https://wellknown.network/agents/time-series-forecast-mcp/record.md","api":"https://wellknown.network/api/v1/agents/time-series-forecast-mcp","status":"https://wellknown.network/api/v1/agents/time-series-forecast-mcp/status","claim":"https://wellknown.network/agents/time-series-forecast-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/time-series-forecast-mcp/claim.json","badge":"https://wellknown.network/agents/time-series-forecast-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:time-series-forecast-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"time-series-forecast-mcp","summary":"时间序列预测 MCP (Model Context Protocol) - 提供 AR、MA、ARIMA、GARCH、指数平滑五种时间序列预测能力","description":"# Time Series Forecast MCP \n \n时间序列预测 MCP (Model Context Protocol)，提供五种时间序列预测模型： \n \n- **AR**: 自回归模型 \n- **MA**: 移动平均模型 \n- **ARIMA**: 自回归积分移动平均模型（支持自动选参） \n- **GARCH**: 广义自回归条件异方差模型（波动率预测） \n- **EXPONENTIAL_SMOOTHING**: 指数平滑模型（支持季节性） \n \n## 安装 \n \n```bash \npip install time-series-forecast-mcp \n``` \n \n## 使用 \n \n### 作为 MCP 服务启动 \n \n```bash \npython -m time_series_forecast_mcp \n``` \n \n或使用 fastmcp CLI： \n \n```bash \nfastmcp run server.py:mcp \n``` \n \n### 工具列表 \n \n#### list_forecast_models \n列出支持的时间序列预测模型及适用场景说明。 \n \n#### forecast_time_series \n对历史时间序列进行预测。 \n \n**参数**: \n- `model_type`: AR / MA / ARIMA / GARCH / EXPONENTIAL_SMOOTHING \n- `series`: 历史观测值，按时间升序排列 \n- `horizon`: 向前预测步数（默认 12） \n- `p`: AR 阶数或 ARIMA/GARCH 的 p（可选） \n- `d`: ARIMA 差分阶数（可选） \n- `q`: MA 阶数或 ARIMA/GARCH 的 q（可选） \n- `seasonal_period`: 季节周期，仅 EXPONENTIAL_SMOOTHING 使用（可选） \n- `confidence_level`: 置信水平，默认 0.95 \n \n**返回**: \n- `forecast`: 点预测 \n- `lower_bound / upper_bound`: 置信区间 \n- `model_info`: 模型参数与 AIC/BIC 等信息 \n- `diagnostics`: 样本量等诊断信息 \n \n## 依赖 \n \n- fastmcp >= 2.0.0 \n- numpy >= 1.24.0 \n- pandas >= 2.0.0 \n- statsmodels >= 0.14.0 \n- arch >= 7.0.0 \n- scipy >= 1.10.0 \n \n## 许可证 \n \nMIT License","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["time-series","forecasting","mcp","arima","garch","exponential-smoothing"],"pricing":null,"endpoints":[{"url":"pypi:time-series-forecast-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.weather","name":"Weather","confidence":1,"provenance":"derived"}],"categories":["data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"time-series-forecast-mcp","registry":"pypi","observedAt":"2026-09-10T14:24:24.483Z","publishedAt":"2026-06-08T09:23:41.442284Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"time-series-forecast-mcp","url":"https://pypi.org/project/time-series-forecast-mcp/","firstSeenAt":"2026-09-10T14:22:34.247Z","fetchedAt":"2026-09-10T14:22:34.247Z","normalizedAt":"2026-09-10T14:22:34.247Z"}]},"firstSeenAt":"2026-09-10T14:22:34.247Z","updatedAt":"2026-09-10T14:24:24.483Z"}