---
title: "MCP quickstart weather server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/mcp-quickstart-weather-python/
description: "Looks up US National Weather Service alerts and a five-period forecast over stdio."
---

# MCP quickstart weather server: review, setup & limitations · Undominated.ai

> Looks up US National Weather Service alerts and a five-period forecast over stdio.

[← Explore all mcp servers](/mcp-servers/)

WEATHER LOOKUP / Model Context Protocol a Series of LF Projects, LLC

# MCP quickstart weather server

Looks up US National Weather Service alerts and a five-period forecast over stdio.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/README.md)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 4 linked sources
 Publisher Model Context Protocol a Series of LF Projects, LLC
 Licence [Apache-2.0 / MIT transition; documentation CC-BY-4.0 ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/LICENSE)
 Revision 2912bb30785c
 [Read what was—and wasn’t—checked ↓](#review)

“A simple MCP weather server”

 [Model Context Protocol a Series of LF Projects, LLC · upstream description ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/pyproject.toml) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The server speaks stdio and registers get_alerts and get_forecast. get_alerts requests only api.weather.gov. An empty feature list becomes an empty array.
- Missing alert fields are rewritten to placeholder sentences. The file writes no local file and contains no credential.

### A good fit for

 - Reading a small stdio MCP server whose tools call one public weather API
- Seeing where a second request follows a URL from the first response

### Weigh up before choosing

 - get_forecast's second request uses the forecast URL from the points payload. That host is not pinned to api.weather.gov. Only the first five periods are returned. A missing key in a period would raise.
- make_nws_request returns None on every exception. The tools declare no annotations. uv.lock was not audited. The server was not started. The README command was not executed. Sibling examples were not opened.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - weather-server-python/weather.py
- weather-server-python/pyproject.toml
- weather-server-python/README.md
- LICENSE
- README.md (repository root)

### Our findings

 - pyproject.toml names version 0.1.0, requires Python 3.10 or later, and depends on httpx2, mcp[cli], and pydantic. The script entry is weather:main. weather.py calls mcp.run with transport stdio.
- The root LICENSE describes a transition from MIT to Apache-2.0, CC-BY-4.0 for documentation other than specifications, and then the MIT text. The MIT copyright line is Copyright (c) 2024-2025 Model Context Protocol a Series of LF Projects, LLC. Apache-2.0 is not the only licence in that file.
- The server README says both tools declare an output schema and return structured_content, and that get_alerts returns a top-level JSON array, which protocol revision 2026-07-28 is the first to allow. weather.py builds that array as a RootModel over a list.
- Neither the server README nor the root README at this commit contains a JSON client-configuration block, so no configExample is recorded. The README runs the server with uv run weather.py or through the repository's client examples.
- Health on 2026-10-13: the repository is not archived. GitHub reports its licence as NOASSERTION; the root LICENSE at this commit describes a licensing transition from the MIT License to the Apache License.

### Not established by this review

 - The server was not started.
- No request was sent to api.weather.gov.
- uv.lock was not audited. uv run was not executed.
- The protocol and SDK URLs named in the comments were not opened.
- Sibling language servers and the client examples were not opened.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/README.md)
 - Read the server at the reviewed commit. No install command is published for this record.
- The README shows uv run weather.py. That command was not executed.

### Before you start

 - Python 3.10 or later
- An MCP client that can launch a stdio process you choose

### Compatibility

An MCP client that speaks stdio · For get_alerts, a client on protocol revision 2026-07-28: the README says its array-rooted output schema requires that revision and that the SDK raises rather than adapting it for older clients · Python 3.10 or later, as pyproject.toml requires

### Implementation

Python

### Transports

stdio

### Local stdio process. It calls the National Weather Service and can follow a forecast URL from that response.

 - Speak MCP over stdio
- Send HTTPS GET requests to api.weather.gov
- Send a second HTTPS GET to the forecast URL named by the points response

### Cost model

Source at no charge. The root LICENSE: "All new code and specification contributions to the project are licensed under Apache-2.0", while contributions whose authors have not granted relicensing consent "remain licensed under the MIT License". Documentation contributions are licensed under CC-BY-4.0. Copyright (c) 2024-2025 Model Context Protocol a Series of LF Projects, LLC. This review did not start the server.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Quickstart weather server ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/weather.py) Checked 2026-10-13 https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/weather.py Supports: stdio transport, alert placeholders, five-period forecast
- [Weather server manifest ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/pyproject.toml) Checked 2026-10-13 https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/pyproject.toml Supports: version 0.1.0, Python 3.10, declared dependencies
- [Weather server README ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/README.md) Checked 2026-10-13 https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/weather-server-python/README.md Supports: two tools, stdio transport, structured content and protocol revision 2026-07-28, uv run weather.py
- [Licence file ↗](https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/LICENSE) Checked 2026-10-13 https://github.com/modelcontextprotocol/quickstart-resources/blob/2912bb30785c7702a2f9abfab783e9140aa7246b/LICENSE Supports: MIT terms, Apache-2.0 transition, CC-BY-4.0 documentation note

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### MCP sequential thinking server ↗ Stores one supplied thought in memory and returns counts. It does not check that the thought is right.](/mcp-servers/mcp-server-sequential-thinking/)[### AWS Labs Amazon Translate ↗ Translates text and manages document translation jobs and custom terminology with AWS Translate.](/mcp-servers/awslabs-translate/)[### AWS Labs Finch ↗ Builds and pushes container images through the local Finch CLI, with additional ECR repository support.](/mcp-servers/awslabs-finch/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
