Skip to main content
Glama
deenesjakoruzh
overstarry

qweather-mcp

by overstarry
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

qweather-mcp

English | 简体中文

MCP server for QWeather API, providing comprehensive weather information query capabilities through Model Context Protocol (MCP).

✨ Features

  • 🌤️ Real-time weather queries

  • 📅 Multi-day weather forecasts (3/7/10/15/30 days)

  • 🔐 JWT (EdDSA/Ed25519) and legacy API Key authentication

  • 🔌 Custom API base URL support

  • 🛠️ Complete tool integration

Related MCP server: OpenWeatherMap MCP Server

📦 Installation

Via Smithery

Recommended: Install automatically for Claude Desktop using Smithery:

npx -y @smithery/cli install @overstarry/qweather-mcp --client claude

Manual Configuration

  1. First, get your credentials from the QWeather Console.

  2. Start the server:

# stdio server
npx -y qweather-mcp

  1. Configure environment variables (pick one of the two auth modes below).

🔐 JWT Authentication (recommended)

QWeather has announced that API Key authentication will be deprecated in 2027 and recommends migrating to JWT (EdDSA + Ed25519). Generate an Ed25519 key pair, upload the public key to the QWeather console, and configure:

QWEATHER_API_BASE=https://<your-host>.qweatherapi.com
QWEATHER_PROJECT_ID=<project-id>
QWEATHER_KEY_ID=<credential-id>
# Either pass the PEM path…
QWEATHER_PRIVATE_KEY_PATH=/path/to/ed25519-private.pem
# …or the PEM content directly (newlines preserved)
# QWEATHER_PRIVATE_KEY="-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----"

If both QWEATHER_PRIVATE_KEY_PATH and QWEATHER_PRIVATE_KEY are provided, the path takes precedence. For QWEATHER_PRIVATE_KEY, the literal two-character sequence \n is auto-converted to real newlines, so the single-line form above works in shells, .env files, and JSON configs.

JSON config example:

{
  "mcpServers": {
    "qweather": {
      "command": "npx",
      "args": ["-y", "qweather-mcp"],
      "env": {
        "QWEATHER_API_BASE": "https://<your-host>.qweatherapi.com",
        "QWEATHER_PROJECT_ID": "<project-id>",
        "QWEATHER_KEY_ID": "<credential-id>",
        "QWEATHER_PRIVATE_KEY_PATH": "/path/to/ed25519-private.pem"
      }
    }
  }
}

JWT details: tokens are signed with alg=EdDSA, iat is back-dated 30s to tolerate clock skew, exp = iat + 900s (15 min, well under QWeather's 24h cap), and tokens are cached and reused until ~30s before expiry. See the official authentication docs.

🔑 API Key Authentication (legacy)

QWEATHER_API_BASE=https://api.qweather.com
QWEATHER_API_KEY=<your-api-key>

JSON config example:

{
  "mcpServers": {
    "qweather": {
      "command": "npx",
      "args": ["-y", "qweather-mcp"],
      "env": {
        "QWEATHER_API_BASE": "<your-api-url>",
        "QWEATHER_API_KEY": "<your-api-key>"
      }
    }
  }
}

Mode detection

Env vars present

Mode

Full JWT vars (QWEATHER_PROJECT_ID + QWEATHER_KEY_ID + QWEATHER_PRIVATE_KEY[_PATH])

JWT (wins even if QWEATHER_API_KEY is also set)

Full JWT vars + QWEATHER_API_KEY

JWT (API Key is ignored)

Partial JWT vars + QWEATHER_API_KEY

API Key, with a startup warning to stderr

Partial JWT vars only

startup error

QWEATHER_API_KEY only

API Key

neither

startup error

The active mode is logged to stderr at startup, e.g. Weather MCP Server running on stdio (auth: JWT/EdDSA).

🛠️ Available Tools

get-weather-now

Get current weather information for a specified location.

get-weather-forecast

Get weather forecast information for a specified location with customizable forecast days:

  • 3-day forecast

  • 7-day forecast

  • 10-day forecast

  • 15-day forecast

  • 30-day forecast

Forecast data includes:

  • Temperature range (min/max)

  • Day/night weather conditions

  • Sunrise/sunset times

  • Precipitation

  • Humidity

  • Wind conditions

  • UV index

get-minutely-precipitation

Provides minute-by-minute precipitation forecast for the next 2 hours, including:

  • Precipitation type (rain/snow)

  • Precipitation amount per minute

  • Precise time predictions

  • Real-time forecast descriptions

get-hourly-forecast

Provides hourly weather forecasts for 24, 72, or 168 hours, including:

  • Temperature changes

  • Weather conditions

  • Wind direction and force

  • Relative humidity

  • Atmospheric pressure

  • Precipitation probability

  • Cloud coverage

get-weather-warning

Provides real-time weather warning information, including:

  • Warning issuing authority

  • Warning level and type

  • Detailed warning content

  • Warning validity period

  • Related recommendations

get-weather-indices

Provides weather life indices information, supporting various index types:

  • Sports index

  • Car wash index

  • Dressing index

  • Fishing index

  • UV index

  • Tourism index

  • Allergy index and 16 other life indices

get-air-quality

Provides real-time air quality data, including:

  • AQI index

  • Air quality level

  • Primary pollutants

  • Health advice

  • Pollutant concentrations

get-air-quality-hourly

Provides hourly air quality forecast for the next 24 hours:

  • Hourly AQI predictions

  • Pollutant concentration changes

  • Health impact assessment

  • Protection recommendations

get-air-quality-daily

Provides air quality forecast for the next 3 days:

  • Daily AQI predictions

  • Primary pollutant forecasts

  • Air quality level changes

  • Health protection advice

🤝 Contributing

Issues and improvements are welcome! Please check our contribution guidelines.

📄 License

MIT

🔗 Related Links

Available Tools

2 tools
get-weather-nowC

Get current weather for a location using QWeather API

ParametersJSON Schema
NameRequiredDescriptionDefault
locationYesLocation ID for the city

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. The description implies a read operation but lacks details about API key requirements, error handling, or response format. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise single sentence. Could be improved by adding a hint about the sibling tool or output format without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given low complexity, the description is incomplete. It does not explain how to obtain the location ID or what the output contains, missing essential context for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with the parameter described as 'Location ID for the city'. The description adds no extra parameter info, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get current weather for a location' with a specific API mention. However, it does not differentiate from sibling 'lookup-city', which likely provides city IDs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention that the location parameter might come from the sibling tool 'lookup-city'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

lookup-cityC

Look up city information by name

ParametersJSON Schema
NameRequiredDescriptionDefault
cityNameYesName of the city to look up

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. The description only states the basic action, with no mention of side effects, authentication needs, rate limits, or error handling (e.g., if city not found). This is insufficient for a tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, front-loaded with the action. It could be more structured (e.g., listing what information is returned), but it is not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple lookup tool with one parameter and no output schema, the description does not specify what fields of city information are returned, nor any behavioral context. This leaves the agent uncertain about the response format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (single parameter well-described in schema). The description adds no extra meaning beyond 'by name', but the schema already provides a clear description. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'look up city information by name', specifying verb and resource. However, it does not differentiate from the sibling tool 'get-weather-now', which may also involve city queries. The description lacks detail on what information is returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. No mention of prerequisites, limitations, or cases to avoid. The sibling tool exists but is not differentiated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedget-weather-now
    • First observedlookup-city
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0
Disambiguation5/5

The two tools serve clearly distinct purposes: one retrieves current weather data, and the other looks up city information. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern using snake_case: get-weather-now and lookup-city. The naming is predictable and clear.

Tool Count3/5

With only 2 tools, the set is on the lower end of reasonable. While it covers the basics, it feels minimal for a weather API, which typically includes more operations like forecasts or alerts.

Completeness2/5

The tool set lacks essential weather features such as forecasts, historical data, or severe weather alerts. For a weather-focused server, the absence of these common operations is a notable gap.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

Appeared in Searches

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/overstarry/qweather-mcp'

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