Yandex Weather MCP server (SmartHome)
mcp-yandex-weather
A small MCP server on the Yandex Weather SmartHome API: current weather, daily and hourly forecasts with a free-tier key
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- Only reads public weather data for given coordinates
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/mcp-yandex-weatherDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Assembled automatically, review before installing.
Run in a terminal
claude mcp add --transport stdio --env 'YANDEX_WEATHER_API_KEY=<your YANDEX_WEATHER_API_KEY>' ya-pogoda -- uvx run --directory /path/to/mcp-yandex-weather server.pyOr add to the file .mcp.json, in the project
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Add to the file ~/.cursor/mcp.json, for all projects
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. For a single project, put the same block into .cursor/mcp.json.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Run in a terminal
code --add-mcp '{"name":"ya-pogoda","type":"stdio","command":"uvx","args":["run","--directory","/path/to/mcp-yandex-weather","server.py"],"env":{"YANDEX_WEATHER_API_KEY":"<your YANDEX_WEATHER_API_KEY>"}}'Or add to the file .vscode/mcp.json, in the project
{
"servers": {
"ya-pogoda": {
"type": "stdio",
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the servers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Run in a terminal
codex mcp add ya-pogoda --env 'YANDEX_WEATHER_API_KEY=<your YANDEX_WEATHER_API_KEY>' -- uvx run --directory /path/to/mcp-yandex-weather server.pyOr add to the file ~/.codex/config.toml, for all projects
[mcp_servers.ya-pogoda]
command = "uvx"
args = ["run", "--directory", "/path/to/mcp-yandex-weather", "server.py"]
env = { YANDEX_WEATHER_API_KEY = "<your YANDEX_WEATHER_API_KEY>" }If the file already exists, append the block to the end.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file ~/.gemini/settings.json, for all projects
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file ~/.config/devin/mcp_config.json, for all projects
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. Legacy Cascade keeps the MCP config in ~/.codeium/windsurf/mcp_config.json.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Formerly Windsurf.
Add to the file cline_mcp_settings.json, for all projects
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. Open the settings file in Cline: MCP Servers tab, Configure MCP Servers.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file .roo/mcp.json, in the project
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
A fork of Roo Code, same .roo folders.
Add to the file opencode.json, in the project
{
"mcp": {
"ya-pogoda": {
"type": "local",
"command": [
"uvx",
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"environment": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcp key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file ~/.config/zed/settings.json, for all projects
{
"context_servers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the context_servers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file .codeassistant/mcp.json, in the project
{
"mcpServers": {
"ya-pogoda": {
"command": "uvx",
"args": [
"run",
"--directory",
"/path/to/mcp-yandex-weather",
"server.py"
],
"env": {
"YANDEX_WEATHER_API_KEY": "<your YANDEX_WEATHER_API_KEY>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
YANDEX_WEATHER_API_KEYsecret, required- API key for Yandex Weather SmartHome
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Register in the Yandex Pogoda SmartHome console, get an API key, clone ivanscm/mcp-yandex-weather, copy .env.example to .env with the YANDEX_WEATHER_API_KEY, then add the server to your MCP client config with command uv, args run --directory path server.py.
Other ways from the author
git clone https://github.com/ivanscm/mcp-yandex-weather.git && cd mcp-yandex-weather && cp .env.example .envClone and fill in .env with the YANDEX_WEATHER_API_KEY.
This is third-party code. Review the repository files before installing.
What it does
The server offers three tools: get_current_weather returns temperature, feels-like temperature, wind speed, condition and icon for given coordinates, get_forecast returns a daily forecast for up to two days on the free tier split into night, morning, day and evening, and get_hourly_forecast returns hourly data. There is a weather://current/{lat}/{lon} resource with current weather as JSON and a weather_report prompt for generating a text weather report. The server is built specifically for the Yandex Pogoda B2B SmartHome tariff rather than the general Yandex Weather API; the free tier is limited to a today-and-tomorrow forecast and a basic parameter set.
Who it is for. For people who want a simple Yandex weather integration in an agent: day planning, reports, smart-home automation.
Good fit when
- You want current weather, daily or hourly forecasts by coordinates in agent responses
- The free SmartHome tier with a today-and-tomorrow forecast is enough
- You want HTTP mode for reaching the server from another device on the network
Not a fit when
- You need extended parameters like humidity, pressure or UV index: those require the commercial tier
- You need a forecast beyond two days without a paid tier
Example request
What is the weather in Moscow right now and what is tomorrow's forecastLimitations
You need a Yandex Pogoda SmartHome API key, issued after registering with a phone number and accepting the terms in the Yandex Weather console. The free tier is limited to a today-and-tomorrow forecast, a basic parameter set and a request rate cap per the agreement. The project is small, has one author, and updates infrequently.
How to disable. Remove the ya-pogoda block from claude_desktop_config.json or your MCP client's configuration.
MCP
- Transport
- stdio, http
- Authentication
- API key
| Environment variables | |
|---|---|
| YANDEX_WEATHER_API_KEY required, secret | The Yandex Pogoda SmartHome API key |
Security check
- Only reads public weather data for given coordinates
README in short
The English and Russian README describes the server as a wrapper over the Yandex Weather SmartHome API with three tools, one resource and one prompt. It covers getting a key through the SmartHome console, a table of free versus commercial tier limits, running in stdio and HTTP modes, setup for Claude Desktop, Hermes Agent and Cursor, plus running via MCP Inspector and pytest tests.
FAQ
How many days of free forecast are available?
Today and tomorrow; paid tiers offer more days and parameters.
Can the server run remotely over HTTP?
Yes, with the --http flag, so clients like Hermes connect at http://host:8000/mcp.
Related
A self-hosted knowledge base with block-level references and a built-in MCP server for connecting AI agents to your notes
A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more
Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server
A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI