What can open-meteo-mcp do?

weather-data-retrieval-via-mcp-protocol, geographic-coordinate-resolution, forecast-data-aggregation-and-formatting, historical-weather-data-querying, mcp-protocol-tool-registration-and-invocation, unit-conversion-and-localization, error-handling-and-fallback-strategies, weather-alert-and-extreme-condition-detection

open-meteo-mcp

MCP ServerFree

MCP server: open-meteo-mcp

Open Source

/ 100

8 capabilities

Capabilities8 decomposed

weather-data-retrieval-via-mcp-protocol

Medium confidence

Exposes Open-Meteo weather API endpoints through the Model Context Protocol (MCP), allowing Claude and other MCP-compatible clients to query current weather, forecasts, and historical data without direct HTTP calls. Implements MCP resource and tool abstractions that translate natural language weather requests into Open-Meteo API parameters, handling coordinate lookup, unit conversion, and response formatting automatically.

Solves for

I want Claude to fetch real-time weather data for any location without me managing API keys or HTTP requestsI need to build an AI agent that can answer weather questions by querying live meteorological dataI want to integrate weather context into LLM reasoning chains without writing boilerplate API integration code

Best for

AI agent developers building weather-aware applications

Teams building Claude-powered assistants that need real-time weather context

Developers migrating from REST API calls to MCP-based tool integration

Requires

MCP-compatible client (Claude Desktop, custom MCP client, or compatible LLM interface)

Network connectivity to Open-Meteo API endpoints (api.open-meteo.com)

Node.js runtime or equivalent (specific version depends on implementation — check repository)

Limitations

Depends on Open-Meteo API availability and rate limits (no built-in caching or request batching)

No authentication required by Open-Meteo but MCP server itself has no access control — suitable only for trusted environments

Limited to Open-Meteo's supported geographic coverage and forecast models — cannot query proprietary weather services

What makes it unique

Bridges Open-Meteo's free, open weather API directly into the MCP ecosystem, eliminating the need for custom HTTP client code in LLM applications. Uses MCP's tool and resource abstractions to expose weather queries as first-class capabilities that Claude can invoke naturally, with automatic parameter mapping and response normalization.

vs alternatives

Simpler than building custom REST API wrappers or weather plugins for each LLM framework because it leverages MCP's standardized tool-calling protocol, making it compatible with any MCP client without framework-specific adapters.

geographic-coordinate-resolution

Medium confidence

Translates human-readable location names (cities, regions, addresses) into latitude/longitude coordinates required by Open-Meteo's weather queries. Likely implements geocoding via Open-Meteo's Geocoding API or similar reverse-lookup service, handling ambiguous location names and returning ranked results so the LLM can disambiguate if needed.

Solves for

I want to ask Claude for weather in 'New York' without manually specifying coordinatesI need the MCP server to automatically resolve city names to geographic coordinates for weather lookupsI want to handle ambiguous location names (e.g., multiple cities named 'Springfield') gracefully in weather queries

Best for

Conversational AI agents that accept natural language location inputs

Applications where end-users provide city/region names rather than coordinates

Teams building multi-location weather dashboards or monitoring systems

Requires

Access to Open-Meteo Geocoding API (free, no authentication)

Network connectivity to Open-Meteo endpoints

Limitations

Geocoding accuracy depends on Open-Meteo's underlying geographic database — may not resolve very small towns or recent administrative boundary changes

Ambiguous location names return multiple candidates, requiring additional LLM reasoning to select the correct one (adds latency)

No support for custom location aliases or user-defined place names — always resolves against standard geographic databases

What makes it unique

Integrates geocoding as a transparent preprocessing step within the MCP protocol layer, so Claude can accept natural language locations without explicit coordinate parameters. Handles the full resolution pipeline (name → candidates → selection) within the MCP tool abstraction.

vs alternatives

More seamless than requiring users to manually specify coordinates or implement separate geocoding logic, because it's built into the MCP tool interface and handles disambiguation automatically through LLM reasoning.

forecast-data-aggregation-and-formatting

Medium confidence

Retrieves multi-day or hourly weather forecasts from Open-Meteo and formats them into structured, LLM-friendly representations. Handles variable selection (temperature, precipitation, wind, etc.), time-series aggregation, unit conversion (Celsius/Fahrenheit, metric/imperial), and response truncation to fit within LLM context windows. May implement caching of recent forecasts to reduce API calls.

Solves for

I want Claude to provide a 7-day weather forecast for a location in a single, coherent responseI need hourly weather data formatted as a time-series that Claude can reason about and summarizeI want to specify which weather variables (temperature, rain, wind) to include in the forecast to save context tokens

Best for

Weather chatbots and conversational assistants

Multi-day planning agents that need forecast context

Applications with strict context window limits that need selective weather data

Requires

Open-Meteo API access

MCP client capable of handling structured JSON responses with nested time-series data

Limitations

Forecast accuracy degrades beyond 10-14 days (Open-Meteo limitation, not MCP server)

No built-in caching — repeated queries for the same location/time incur full API latency

Large hourly forecasts (e.g., 30+ days × 24 hours) may exceed LLM context limits even after truncation

What makes it unique

Implements forecast aggregation and formatting as part of the MCP tool response pipeline, so Claude receives pre-processed, context-aware weather data rather than raw API responses. Likely includes intelligent variable selection and context-window-aware truncation to maximize relevance within LLM constraints.

vs alternatives

More efficient than having Claude parse raw Open-Meteo JSON responses because the MCP server handles formatting, unit conversion, and context optimization, reducing token overhead and improving response quality.

historical-weather-data-querying

Medium confidence

Provides access to historical weather records from Open-Meteo's archive, allowing queries for past weather conditions at any location and date. Implements time-range filtering, variable selection, and aggregation (daily, weekly, monthly summaries) to support weather analysis, trend detection, and climate pattern reasoning by LLMs.

Solves for

I want Claude to analyze historical weather patterns for a location to inform climate or agricultural decisionsI need to retrieve past weather data for a specific date range to validate forecasts or investigate anomaliesI want to compare current conditions against historical averages to contextualize weather events

Best for

Climate analysis and historical weather research agents

Agricultural or energy planning systems that need historical context

Anomaly detection systems comparing current conditions to historical baselines

Requires

Open-Meteo historical weather API access

Valid date ranges within Open-Meteo's archive coverage

Limitations

Historical data availability varies by location — some regions have limited archives (Open-Meteo limitation)

Queries spanning very long time ranges (e.g., 10+ years) return large datasets that may exceed context limits

No built-in statistical aggregation (e.g., percentiles, anomaly scores) — Claude must perform analysis on raw data

What makes it unique

Extends the MCP weather integration beyond real-time forecasts to include historical archives, enabling LLMs to perform temporal reasoning and trend analysis. Implements date-range filtering and aggregation within the MCP tool layer, abstracting Open-Meteo's historical API complexity.

vs alternatives

Provides historical context that real-time-only weather APIs lack, allowing Claude to perform comparative analysis and anomaly detection without requiring separate climate data sources or manual data aggregation.

mcp-protocol-tool-registration-and-invocation

Medium confidence

Implements the MCP server-side tool registration and invocation framework, exposing weather capabilities as MCP tools that Claude and other MCP clients can discover and call. Handles tool schema definition (parameters, return types), request routing, error handling, and response serialization according to the MCP specification. Likely uses an MCP SDK or framework (e.g., mcp-python, mcp-node) to manage the protocol handshake and message passing.

Solves for

I want Claude to automatically discover available weather tools without manual configurationI need the MCP server to handle tool invocation requests from Claude and return properly formatted responsesI want to add new weather capabilities (e.g., air quality, UV index) as MCP tools without rewriting the protocol layer

Best for

MCP server developers building integrations with Claude or other LLM clients

Teams standardizing on MCP for AI tool integration across multiple services

Developers extending open-meteo-mcp with additional weather or environmental data sources

Requires

MCP SDK compatible with the server's language (Node.js, Python, etc.)

MCP client that supports tool calling (Claude Desktop, custom MCP client)

Proper MCP server initialization and lifecycle management

Limitations

MCP protocol overhead adds ~50-200ms per tool invocation compared to direct function calls

Tool schema must be statically defined at server startup — no dynamic tool generation based on runtime state

Error handling is limited to MCP error codes and messages — no custom exception types or detailed debugging info

What makes it unique

Implements the MCP server-side framework that bridges Open-Meteo's REST API and Claude's tool-calling interface, handling all protocol-level concerns (schema registration, request routing, serialization) so weather tools appear as native capabilities to the LLM.

vs alternatives

Cleaner than custom REST API wrappers because MCP's standardized tool protocol eliminates the need for framework-specific adapters, making the server compatible with any MCP client without modification.

unit-conversion-and-localization

Medium confidence

Automatically converts weather data between unit systems (Celsius/Fahrenheit, metric/imperial wind speeds, millimeters/inches precipitation) and formats output according to user preferences or locale. Implements unit mapping tables and conversion logic within the response formatting pipeline, ensuring Claude receives data in the requested system without manual transformation.

Solves for

I want weather data in Fahrenheit and imperial units for US-based usersI need the MCP server to automatically convert metric weather data to imperial for compatibility with legacy systemsI want to support multiple locales and unit preferences without hardcoding conversions in Claude's prompts

Best for

Multi-region weather applications serving users with different unit preferences

Teams integrating weather data into systems expecting specific unit systems

Conversational agents that need to adapt output format to user locale

Requires

Unit preference specification (metric or imperial)

Locale or region identifier for formatting

Limitations

Unit conversion is applied uniformly across all responses — no per-variable customization

Locale-specific formatting (e.g., date formats, number separators) may not align with all regional standards

Conversion precision is limited to typical weather reporting accuracy (e.g., 1°F, 1 mph) — not suitable for scientific applications requiring higher precision

What makes it unique

Integrates unit conversion and localization into the MCP response pipeline, so Claude receives pre-formatted data matching user preferences without needing to handle conversion logic. Supports both metric and imperial systems transparently.

vs alternatives

More user-friendly than requiring Claude to perform unit conversions in prompts because the MCP server handles all formatting, reducing token overhead and improving response consistency across different locales.

error-handling-and-fallback-strategies

Medium confidence

Implements robust error handling for Open-Meteo API failures, network timeouts, invalid location queries, and out-of-range date requests. Provides meaningful error messages to Claude and may implement fallback strategies (e.g., returning cached data, degrading to lower-resolution forecasts, or suggesting alternative locations). Handles MCP protocol errors and ensures the server remains stable under adverse conditions.

Solves for

I want Claude to gracefully handle weather API failures without crashing the conversationI need informative error messages when a location cannot be resolved or data is unavailableI want the MCP server to retry failed requests or use cached data when the API is temporarily unavailable

Best for

Production weather agents that must handle API outages gracefully

Applications requiring high availability and resilience

Teams building user-facing weather assistants that need clear error communication

Requires

Timeout configuration for API calls

Optional cache storage for fallback data

Error logging and monitoring infrastructure

Limitations

Fallback strategies (e.g., cached data) may return stale information — no guarantee of freshness

Retry logic adds latency and may not recover from persistent API failures

Error messages are limited to MCP protocol constraints — cannot provide detailed debugging info to end-users

What makes it unique

Implements error handling at the MCP server layer, ensuring Claude receives clear, actionable error messages and can decide whether to retry, use fallback data, or inform the user. Abstracts API-level failures from the LLM, improving robustness.

vs alternatives

More reliable than exposing raw API errors to Claude because the MCP server handles retries, caching, and error translation, reducing the likelihood of conversation failures due to transient API issues.

weather-alert-and-extreme-condition-detection

Medium confidence

Analyzes forecast data to identify extreme weather conditions (severe storms, heat waves, cold snaps, high wind, etc.) based on configurable thresholds. Implements condition detection logic that flags dangerous weather patterns and returns structured alerts with severity levels, allowing agents to proactively warn users or trigger contingency workflows. Detection rules can be customized per location or use case.

Solves for

I want to be alerted if severe weather is forecast for my locationI need to identify heat waves or cold snaps in historical dataI want my agent to automatically cancel outdoor events if dangerous weather is predicted

Best for

Safety-critical applications (emergency response, event planning)

Proactive notification systems that warn users of dangerous conditions

Agents that need to make weather-dependent decisions automatically

Requires

Forecast data from Open-Meteo

Configurable alert threshold definitions (temperature, wind speed, precipitation, etc.)

Limitations

Alert thresholds are static or require manual configuration; no machine learning-based anomaly detection

Detection is based on single-variable thresholds; complex multi-variable conditions require custom logic

No integration with official weather alerts (NWS, MeteoAlarm, etc.) — only Open-Meteo forecast data

What makes it unique

Implements configurable alert detection on top of Open-Meteo forecast data within the MCP server, allowing Claude to request 'alerts for dangerous weather' as a single tool call rather than fetching raw forecast and implementing detection logic separately

vs alternatives

More integrated than requiring agents to implement alert logic themselves; more flexible than hardcoded alert rules because thresholds can be customized per use case

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with open-meteo-mcp, ranked by overlap. Discovered automatically through the match graph.

MCP Server31

weathermcpmvk

MCP server: weathermcpmvk

historical weather data queryingweather forecast aggregationweather data retrieval via mcp integration

3 shared capabilities

MCP Server24

weather-mcp-server

MCP server: weather-mcp-server

weather-data-retrieval-via-mcp-protocolforecast-data-aggregation-and-formatting

2 shared capabilities

MCP Server24

weather_mcp

MCP server: weather_mcp

weather data retrieval via mcpmulti-source weather data aggregation

2 shared capabilities

MCP Server22

weather-mcp-server

MCP server: weather-mcp-server

historical weather data analysisreal-time weather data retrieval

2 shared capabilities

MCP Server23

weather-mcp-server_test

MCP server: weather-mcp-server_test

weather-data-retrieval-via-mcp-protocolweather-forecast-data-aggregation

2 shared capabilities

MCP Server23

andy-weather-mcp-server

MCP server: andy-weather-mcp-server

weather-data-retrieval-via-mcp-protocolweather-forecast-data-aggregation

2 shared capabilities

Best For

✓AI agent developers building weather-aware applications
✓Teams building Claude-powered assistants that need real-time weather context
✓Developers migrating from REST API calls to MCP-based tool integration
✓Conversational AI agents that accept natural language location inputs
✓Applications where end-users provide city/region names rather than coordinates
✓Teams building multi-location weather dashboards or monitoring systems
✓Weather chatbots and conversational assistants
✓Multi-day planning agents that need forecast context

Known Limitations

⚠Depends on Open-Meteo API availability and rate limits (no built-in caching or request batching)
⚠No authentication required by Open-Meteo but MCP server itself has no access control — suitable only for trusted environments
⚠Limited to Open-Meteo's supported geographic coverage and forecast models — cannot query proprietary weather services
⚠Response latency includes both Open-Meteo API call time and MCP protocol serialization overhead
⚠Geocoding accuracy depends on Open-Meteo's underlying geographic database — may not resolve very small towns or recent administrative boundary changes
⚠Ambiguous location names return multiple candidates, requiring additional LLM reasoning to select the correct one (adds latency)

Requirements

MCP-compatible client (Claude Desktop, custom MCP client, or compatible LLM interface)Network connectivity to Open-Meteo API endpoints (api.open-meteo.com)Node.js runtime or equivalent (specific version depends on implementation — check repository)Access to Open-Meteo Geocoding API (free, no authentication)Network connectivity to Open-Meteo endpointsOpen-Meteo API accessMCP client capable of handling structured JSON responses with nested time-series dataOpen-Meteo historical weather API access

Input / Output

Accepts: natural language location queries (e.g., 'weather in London'), structured geographic parameters (latitude, longitude, or ISO country codes), forecast time ranges and weather variable specifications, location name strings (city, region, country), partial or fuzzy location queries, geographic coordinates (latitude, longitude), forecast duration (days or hours), weather variable selection (temperature, precipitation, wind speed, etc.), unit preferences (metric or imperial), geographic coordinates, start and end dates (ISO 8601 format or natural language), weather variables to retrieve, aggregation level (daily, weekly, monthly), MCP tool call requests with structured parameters, MCP protocol messages (JSON-RPC format), unit system preference (metric, imperial, or mixed), locale identifier (e.g., 'en-US', 'de-DE'), API responses (success or error), network conditions and timeouts, forecast data (JSON), alert threshold configuration (object with min/max values for each variable)

Produces: structured JSON weather data (temperature, precipitation, wind speed, etc.), formatted text summaries suitable for LLM context, time-series forecast arrays with hourly or daily granularity, structured location objects with latitude, longitude, name, country, and confidence metadata, ranked lists of candidate locations for disambiguation, structured forecast objects with time-indexed weather variables, formatted text summaries (e.g., 'High of 72°F, 30% chance of rain'), time-series arrays suitable for charting or further analysis, time-series historical weather data, aggregated statistics (daily averages, min/max, totals), formatted historical summaries for LLM analysis, MCP tool response messages with results or errors, tool schema definitions (JSON Schema format), weather data in requested unit system, formatted strings with locale-appropriate separators and symbols, error messages suitable for LLM processing, fallback data (cached or degraded), retry signals or circuit-breaker states, JSON alert array with severity levels, affected time periods, and variable values

UnfragileRank

Adoption5%(25% weight)

Quality16%(25% weight)

Ecosystem59%(15% weight)

Match Graph25%(30% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

8 capabilities

Visit open-meteo-mcp→

Repository Details

About

MCP server: open-meteo-mcp

Alternatives to open-meteo-mcp

Supabase69Platform

Search the Supabase docs for up-to-date guidance and troubleshoot errors quickly. Manage organizations, projects, databases, and Edge Functions, including migrations, SQL, logs, advisors, keys, and type generation, in one flow. Create and manage development branches to iterate safely, confirm costs

Compare →

Tavily MCP Server62MCP Server

AI-optimized web search and content extraction via Tavily MCP.

Compare →

MongoDB MCP Server62MCP Server

Query and manage MongoDB databases and collections via MCP.

Compare →

Firecrawl MCP Server62MCP Server

Scrape websites and extract structured data via Firecrawl MCP.

Compare →

Are you the builder of open-meteo-mcp?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

smithery

Looking for something else?

Search →

Capabilities8 decomposed

weather-data-retrieval-via-mcp-protocol

Medium confidence

Solves for

Best for

AI agent developers building weather-aware applications

Teams building Claude-powered assistants that need real-time weather context

Developers migrating from REST API calls to MCP-based tool integration

Requires

MCP-compatible client (Claude Desktop, custom MCP client, or compatible LLM interface)

Network connectivity to Open-Meteo API endpoints (api.open-meteo.com)

Node.js runtime or equivalent (specific version depends on implementation — check repository)

Limitations

Depends on Open-Meteo API availability and rate limits (no built-in caching or request batching)

No authentication required by Open-Meteo but MCP server itself has no access control — suitable only for trusted environments

Limited to Open-Meteo's supported geographic coverage and forecast models — cannot query proprietary weather services

What makes it unique

vs alternatives

geographic-coordinate-resolution

Medium confidence

Solves for

Best for

Conversational AI agents that accept natural language location inputs

Applications where end-users provide city/region names rather than coordinates

Teams building multi-location weather dashboards or monitoring systems

Requires

Access to Open-Meteo Geocoding API (free, no authentication)

Network connectivity to Open-Meteo endpoints

Limitations

Geocoding accuracy depends on Open-Meteo's underlying geographic database — may not resolve very small towns or recent administrative boundary changes

Ambiguous location names return multiple candidates, requiring additional LLM reasoning to select the correct one (adds latency)

No support for custom location aliases or user-defined place names — always resolves against standard geographic databases

What makes it unique

vs alternatives

forecast-data-aggregation-and-formatting

Medium confidence

Solves for

Best for

Weather chatbots and conversational assistants

Multi-day planning agents that need forecast context

Applications with strict context window limits that need selective weather data

Requires

Open-Meteo API access

MCP client capable of handling structured JSON responses with nested time-series data

Limitations

Forecast accuracy degrades beyond 10-14 days (Open-Meteo limitation, not MCP server)

No built-in caching — repeated queries for the same location/time incur full API latency

Large hourly forecasts (e.g., 30+ days × 24 hours) may exceed LLM context limits even after truncation

What makes it unique

vs alternatives

historical-weather-data-querying

Medium confidence

Solves for

Best for

Climate analysis and historical weather research agents

Agricultural or energy planning systems that need historical context

Anomaly detection systems comparing current conditions to historical baselines

Requires

Open-Meteo historical weather API access

Valid date ranges within Open-Meteo's archive coverage

Limitations

Historical data availability varies by location — some regions have limited archives (Open-Meteo limitation)

Queries spanning very long time ranges (e.g., 10+ years) return large datasets that may exceed context limits

No built-in statistical aggregation (e.g., percentiles, anomaly scores) — Claude must perform analysis on raw data

What makes it unique

vs alternatives

mcp-protocol-tool-registration-and-invocation

Medium confidence

Solves for

Best for

MCP server developers building integrations with Claude or other LLM clients

Teams standardizing on MCP for AI tool integration across multiple services

Developers extending open-meteo-mcp with additional weather or environmental data sources

Requires

MCP SDK compatible with the server's language (Node.js, Python, etc.)

MCP client that supports tool calling (Claude Desktop, custom MCP client)

Proper MCP server initialization and lifecycle management

Limitations

MCP protocol overhead adds ~50-200ms per tool invocation compared to direct function calls

Tool schema must be statically defined at server startup — no dynamic tool generation based on runtime state

Error handling is limited to MCP error codes and messages — no custom exception types or detailed debugging info

What makes it unique

vs alternatives

unit-conversion-and-localization

Medium confidence

Solves for

Best for

Multi-region weather applications serving users with different unit preferences

Teams integrating weather data into systems expecting specific unit systems

Conversational agents that need to adapt output format to user locale

Requires

Unit preference specification (metric or imperial)

Locale or region identifier for formatting

Limitations

Unit conversion is applied uniformly across all responses — no per-variable customization

Locale-specific formatting (e.g., date formats, number separators) may not align with all regional standards

Conversion precision is limited to typical weather reporting accuracy (e.g., 1°F, 1 mph) — not suitable for scientific applications requiring higher precision

What makes it unique

vs alternatives

error-handling-and-fallback-strategies

Medium confidence

Solves for

Best for

Production weather agents that must handle API outages gracefully

Applications requiring high availability and resilience

Teams building user-facing weather assistants that need clear error communication

Requires

Timeout configuration for API calls

Optional cache storage for fallback data

Error logging and monitoring infrastructure

Limitations

Fallback strategies (e.g., cached data) may return stale information — no guarantee of freshness

Retry logic adds latency and may not recover from persistent API failures

Error messages are limited to MCP protocol constraints — cannot provide detailed debugging info to end-users

What makes it unique

vs alternatives

weather-alert-and-extreme-condition-detection

Medium confidence

Solves for

Best for

Safety-critical applications (emergency response, event planning)

Proactive notification systems that warn users of dangerous conditions

Agents that need to make weather-dependent decisions automatically

Requires

Forecast data from Open-Meteo

Configurable alert threshold definitions (temperature, wind speed, precipitation, etc.)

Limitations

Alert thresholds are static or require manual configuration; no machine learning-based anomaly detection

Detection is based on single-variable thresholds; complex multi-variable conditions require custom logic

No integration with official weather alerts (NWS, MeteoAlarm, etc.) — only Open-Meteo forecast data

What makes it unique

vs alternatives

More integrated than requiring agents to implement alert logic themselves; more flexible than hardcoded alert rules because thresholds can be customized per use case

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to open-meteo-mcp

Supabase69Platform

Compare →

Tavily MCP Server62MCP Server

AI-optimized web search and content extraction via Tavily MCP.

Compare →

MongoDB MCP Server62MCP Server

Query and manage MongoDB databases and collections via MCP.

Compare →

Firecrawl MCP Server62MCP Server

Scrape websites and extract structured data via Firecrawl MCP.

Compare →

open-meteo-mcp

Capabilities8 decomposed

weather-data-retrieval-via-mcp-protocol

geographic-coordinate-resolution

forecast-data-aggregation-and-formatting

historical-weather-data-querying

mcp-protocol-tool-registration-and-invocation

unit-conversion-and-localization

error-handling-and-fallback-strategies

weather-alert-and-extreme-condition-detection

Related Artifactssharing capabilities

weathermcpmvk

weather-mcp-server

weather_mcp

weather-mcp-server

weather-mcp-server_test

andy-weather-mcp-server

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Repository Details

About

Categories

Alternatives to open-meteo-mcp

Are you the builder of open-meteo-mcp?

Get the weekly brief

Data Sources

open-meteo-mcp

Capabilities8 decomposed

weather-data-retrieval-via-mcp-protocol

geographic-coordinate-resolution

forecast-data-aggregation-and-formatting

historical-weather-data-querying

mcp-protocol-tool-registration-and-invocation

unit-conversion-and-localization

error-handling-and-fallback-strategies

weather-alert-and-extreme-condition-detection

Related Artifactssharing capabilities

weathermcpmvk

weather-mcp-server

weather_mcp

weather-mcp-server

weather-mcp-server_test

andy-weather-mcp-server

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Repository Details

About

Categories

Alternatives to open-meteo-mcp

Are you the builder of open-meteo-mcp?

Get the weekly brief

Data Sources