Weather-Prediction MCP Server + Agent Bricks Agent

Weather-Prediction MCP Server + Agent Bricks Agent

A custom MCP server (FastMCP, streamable HTTP) exposing weather tools backedby Open-Meteo, plus a Databricks Agent Bricks agent that uses those toolsto answer natural-language weather questions and make simple predictions.

Built on the Day-3 pattern (Alpaca paper-trading MCP server): thin @mcp.toolfunctions delegating all HTTP/parsing to an adapter module, deployed as aDatabricks App and registered as an external MCP for an agent.

Architecture

Agent Bricks agent  --(MCP tool calls, streamable HTTP)-->  weather_mcp_server.py
                                                                   |
                                                                   v
                                                             weather_broker.py  --(HTTPS)-->  Open-Meteo API

• weather_mcp_server.py — FastMCP server; thin tools, served over streamableHTTP at /mcp.
• weather_broker.py — adapter: all HTTP calls + JSON parsing live here (samerole as alpaca_broker.py). No MCP knowledge.
• The agent calls tools; the server calls Open-Meteo; results flow back as JSON.

Weather API + auth

Open-Meteo (https://open-meteo.com) — no signup, no API key, ~10,000calls/day for non-commercial use. Chosen because it needs zero credentials, sothere are no Databricks secrets to manage for this project, and it bundlesgeocoding + current conditions + multi-day forecast in one keyless API. Worksglobally (not US-only). Endpoints used:

• Geocoding: https://geocoding-api.open-meteo.com/v1/search
• Forecast/current: https://api.open-meteo.com/v1/forecast

Because there is no key, there is nothing secret in this repo.

Tools

location accepts a city name ("Chicago", "Austin, TX", "London") or a raw"lat,lon" pair. when accepts "today", "tomorrow", or an ISO date.

The prediction tool does real reasoning (not a passthrough)

predict_umbrella_needed applies an explicit rule to the target day's forecast:

umbrella_needed = True if precipitation_probability >= 40% ORprecipitation_sum >= 1.0 mm.

The probability catches "might rain" days; the millimetre floor catches dayswhere the chance looks modest but meaningful rain is still expected. The toolreturns the boolean and a reason string naming which threshold fired, sothe agent (and the user) can see why. get_travel_recommendation layers ontemperature and wind thresholds (hot ≥ 35 °C, freezing ≤ 0 °C, windy ≥ 40 km/h,wet ≥ 60% or 10 mm) to produce a headline plus a bring list.

Error handling

A bad location or an API outage returns a clean {"error": "..."} dict, never astack trace, so the agent can react (ask the user to clarify, or report theoutage) instead of failing. Example: get_current_weather("notaplace") →{"error": "Could not find a location named 'notaplace'."}.

Files

• weather_mcp_server.py — FastMCP server (5 tools; 3 required + 2 stretch)
• weather_broker.py — Open-Meteo adapter (all HTTP/parsing)
• test_weather.py — local sanity test (no MCP/Databricks needed)
• requirements.txt / app.yaml — Databricks App config
• AGENT_SYSTEM_PROMPT.md — the agent's system prompt + tool guidance

Setup

1. Test locally (optional, no credentials)

pip install -r requirements.txt
python test_weather.py           # hits Open-Meteo directly, prints results
python weather_mcp_server.py     # serves MCP at http://localhost:8000/mcp

2. Deploy the MCP server as a Databricks App

Push this folder to a Git repo, add it as a Git folder in Databricks, then:Compute → Apps → Create app → Custom, name it starting with mcp-(e.g. mcp-weather), and point it at this folder (which contains app.yaml).Databricks apps listen on port 8000 by default and expose the MCP endpoint athttps://<app-url>/mcp. No secret configuration is needed (Open-Meteo iskeyless).

3. Register it as an external MCP

AI Gateway → MCPs → Add MCP, paste the app's /mcp URL (streamable HTTP),name it weather-tools, and save. Databricks introspects and lists the 5 tools.

4. Build the Agent Bricks agent

Agents → Agent Bricks → Create agent (Custom LLM). Under Tools, add theweather-tools MCP server. Paste the system prompt fromAGENT_SYSTEM_PROMPT.md. Evaluate, then deploy and chat.

Demo — 3 natural-language questions

These are the questions to ask the deployed agent (screenshot the tool-calling +final answers). Sample tool outputs below are from a real run.

1. "Will it rain in Seattle today — should I bring an umbrella?"→ agent calls predict_umbrella_needed("Seattle", "today") →{"umbrella_needed": false, "precipitation_probability": 0, "precipitation_mm": 0.0, "reason": "No umbrella needed: only 0% chance and 0.0 mm expected, both below the thresholds (40% / 1.0 mm)..."} → agent answers: "No umbrella needed in Seattletoday — 0% chance of rain, overcast but dry."

2. "What's the 3-day forecast for Austin, and is it a good idea to travel there tomorrow?"→ get_forecast("Austin, TX", 3) then get_travel_recommendation("Austin, TX", "tomorrow")→ recommendation "Very hot — hydrate and avoid prolonged midday sun" withbring: ["water"] (highs near 37 °C) → agent summarizes the three days and theheat advice.

3. "Which is warmer right now, Chicago, Miami, or Denver?"→ compare_cities(["Chicago","Miami","Denver"]) →warmest: "Denver" (33.6 °C vs Miami 28.0 °C, Chicago 22.2 °C) → agent answerswith the ranking and current conditions.

Notes / limitations

• Open-Meteo forecasts are model output; the prediction tools apply simple,transparent thresholds rather than a trained model — the point is explainablereasoning, easily tuned in weather_mcp_server.py.
• Temperatures are °C and wind km/h (Open-Meteo defaults); add temperature_unit/ wind_speed_unit params in the adapter for Fahrenheit/mph if desired.
• Stretch ideas: severe-weather alerts (layer in the NWS /alerts API for USlocations), historical lookup (Open-Meteo archive API), or a small dashboardapp that logs agent queries.