Skip to main content
Glama
天机气象 · 电力提示 MCP

天机气象 · 电力提示 MCP

by txZheng

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TJW_API_KEYYesTIANJI Weather API key.
TJW_BASE_URLNoBase URL for the TIANJI Weather /v2 API.https://api.tjweather.com/v2
TJW_MAX_CALLSNoProcess-level API call budget; default 20.20
TJW_SUBSCRIPTION_IDYesSubscription ID required by the /v2 endpoint (also accepts real_sub_id).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

面向电力行业的天气提示工具,提供大风、覆冰、低温、高温、强降水、云遮挡等提示,以及基于默认功率曲线的理论出力演示。坐标格式为 '经度,纬度',经度在前。所有结果都带触发条件与证据,请把 data_gaps 一并转述,不要省略。

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_capabilityA

查看已授权要素、已知不可用要素、调用预算与端点。开工前先调用它,避免浪费额度。

power_weather_hintB

指定点位的电力气象提示:大风/覆冰/低温/高温/强降水/云遮挡,按事件合并并给出触发条件。scenario 可选 wind(风电)/pv(光伏)/grid(电网)/general。

wind_solar_snapshotC

风电/光伏关心的关键要素逐时快照(含轮毂风速、露点、风力等级等派生量)。

theoretical_powerA

理论出力演示(非功率预测)。kind=wind 按功率曲线把风速映射为出力,切入/额定/切出、轮毂高度、容量、自定义 curve 均可指定;kind=pv 按辐照度×性能比×温度修正算光伏出力,pr/tilt_gain 可指定。

get_datasetA

唯一的取数入口:返回该窗口内全部已授权要素(服务端不支持筛选,故一次取全)。其他加工类工具会复用同一份缓存,不需要先调用本工具。fields 可选,用于投影列;limit>0 时只截断本次返回的行数,不影响缓存与其他工具计算所用的完整数据。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 5 tools

Disambiguation4/5

Each tool has a fairly clear niche: get_capability is a meta/preflight check, power_weather_hint is event-driven alerts by scenario, theoretical_power is a curve-based demo, and get_dataset is the raw fetch. The only real ambiguity is between wind_solar_snapshot and get_dataset, since both return wind/solar time series — the descriptions differentiate them (derived quantities vs. full authorized fields) but an agent could still hesitate.

Naming Consistency3/5

All names are snake_case, which is good, but the verb conventions are mixed: get_capability and get_dataset use a verb_noun pattern while wind_solar_snapshot and theoretical_power are bare noun phrases and power_weather_hint is noun+noun. It remains readable but not predictable from the name alone.

Tool Count4/5

Five tools is a tight, well-scoped surface for a focused power-weather domain, with each tool covering a distinct layer (capability, raw data, derived snapshot, hints, theoretical output). It is slightly on the lean side, with no tool for listing sites or forecast horizons, but nothing feels redundant.

Completeness4/5

The surface covers preflight authorization checks, raw data retrieval, derived wind/solar snapshots, event-based hazard hints, and theoretical output — the core workflow is closed. Minor gaps remain: no true power forecast (explicitly disclaimed), no site/station discovery or unit/metadata tool, so agents must already know the target location and elements.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues