# Mood Pattern Detector MCP

> Mood Pattern Detector identifies recurring emotional trends and correlates them with lifestyle data. It analyzes historical logs to uncover cyclical patterns—for instance, pinpointing days of the week linked to lower moods. You can measure how variables like sleep or exercise specifically influence your emotional state, and it flags dates where your mood significantly deviates from your established baseline.

## Overview
- **Category:** productivity
- **Price:** Free
- **Tags:** mood, patterns, sentiment, lifestyle, analytics

## Description

This MCP reads through your historical mood records, looking for deep, reliable patterns that are hard to spot manually. Instead of just seeing a dip in mood on a Tuesday, the detector can tell you *why*—it might be linked to poor sleep two nights prior or a specific type of activity. It doesn't guess; it calculates correlations between your emotional state and external factors. You use this connector through Vinkius to get clear insights into what actually moves the needle for your well-being. The system pinpoints daily cycles, measures how exercise affects mood levels, and flags any significant deviations from your normal patterns, giving you a clearer picture of your personal rhythms.

## Tools

### analyze_weekly_cycle
Checks your logs to see if certain days of the week consistently correlate with better or worse moods.

### evaluate_activity_impact
Measures exactly how a specific variable, like sleep duration or exercise time, influences your mood levels.

### identify_mood_anomalies
Flags dates where your reported mood was significantly different from the average trend for that period.

## Prompt Examples

**Prompt:** 
```
Are there any specific days of the week where my mood tends to be lower?
```

**Response:** 
```
The `analyze_weekly_cycle` tool would examine your logs and return the day with the lowest average mood score, such as identifying a 'Monday Slump'.
```

**Prompt:** 
```
Does my exercise routine affect my emotional well-being?
```

**Response:** 
```
By using `evaluate_activity_impact` with 'exercise' as the variable, the tool will compare your average mood on days you exercised versus days you did not.
```

**Prompt:** 
```
Check if there were any unusual spikes or drops in my mood recently.
```

**Response:** 
```
The `identify_mood_anomalies` tool will scan your historical data and list specific dates where your mood was significantly higher or lower than your norm.
```

## Capabilities

### Pinpoint weekly emotional trends
Determine which days or times of the week consistently correlate with specific emotional states.

### Measure variable influence on mood
Quantify how changes in recorded activities, like sleep duration or workout intensity, affect your average mood score.

### Flag sudden mood shifts
Automatically identify specific dates where your emotional state was significantly different from your historical norm.

### Analyze cyclical patterns
Uncover repeating behavioral or emotional cycles over time, such as a recurring 'Sunday Scaries' pattern.

## Use Cases

### The inconsistent energy levels
A user notices they feel low every Friday afternoon, but can't prove why. They run `analyze_weekly_cycle`, which confirms a measurable dip starting Thursday, suggesting the issue isn't just 'Friday fatigue'.

### Optimizing workout routines
A personal trainer needs to know if running or lifting weights has a greater mood impact. They use `evaluate_activity_impact` and find that strength training yields significantly better scores than long-distance cardio.

### Investigating sudden burnout
After weeks of feeling 'off,' the user runs `identify_mood_anomalies`. The tool flags a cluster of low scores starting two months ago, pointing to a specific life stressor they hadn't connected to their mood.

## Benefits

- Stop guessing about mood triggers. `evaluate_activity_impact` tells you, with data, whether adding 30 minutes of cardio actually improves your average daily score.
- Spot predictable dips. The `analyze_weekly_cycle` tool flags recurring patterns—like the 'Sunday Slump'—allowing you to prep for them before they happen.
- Catch unusual events immediately. Use `identify_mood_anomalies` when a major life event or sudden change in routine causes your mood to spike or drop unexpectedly.
- Go beyond simple metrics. Instead of just seeing low moods, this MCP connects those lows to potential culprits, like poor sleep cycles.
- Reduce manual data crunching. You don't have to build complex spreadsheets; the detector handles the correlation math for you.

## How It Works

The bottom line is you get structured data showing which specific lifestyle changes cause measurable shifts in your mood scores.

1. Connect your historical mood logs and lifestyle data sources to the MCP.
2. Run the analysis tool to calculate correlations between recorded variables (e.g., sleep score, exercise minutes) and your reported moods.
3. Review the output reports that identify patterns, measure impacts, or flag anomalies for immediate review.

## Frequently Asked Questions

**How does the analyze_weekly_cycle tool work?**
The `analyze_weekly_cycle` tool scans your historical records to determine if specific days of the week are statistically associated with consistently higher or lower mood scores across your data.

**Can I use evaluate_activity_impact for anything besides exercise?**
No. While it measures how variables influence mood, you must specify a relevant variable (like 'sleep hours' or 'stress score') when running `evaluate_activity_impact`.

**What happens if I run identify_mood_anomalies too often?**
Running this tool frequently is fine, but remember it flags deviations from *your* norm. If you change your lifestyle drastically, the initial anomalies will just reflect that period of transition.

**Do I need to manually clean my data before using Mood Pattern Detector?**
The MCP is designed to ingest existing logs. While cleaner data always helps, it manages basic formatting issues internally when processing the logs.

**What kind of data format does analyze_weekly_cycle require?**
It requires structured mood logs that include timestamps and corresponding mood scores. The tool accepts standard CSV uploads, so just make sure your dates are consistent.

**If I get an error using evaluate_activity_impact, what should I check first?**
First, verify the variable name you passed into the function. The system is case-sensitive and needs a clear match to your recorded activity type.

**Can identify_mood_anomalies run on data from different sources?**
The tool processes all mood logs attached to your Vinkius account, regardless of the original entry source. It consolidates everything before running the analysis.

**How do I optimize my setup for Mood Pattern Detector performance?**
For best results, ensure your historical data set covers at least three full months. More data points allow the tool to build a more accurate baseline model.

**How does the detector identify weekly patterns?**
The `analyze_weekly_pattern` tool calculates the average mood score for each day of the week present in your logs and identifies significant differences between days.

**Can I analyze specific activities like exercise or sleep?**
Yes, using `evaluate_activity_impact`, you can provide the name of any recorded variable to see its correlation with your mood levels.

**What constitutes a mood anomaly?**
An anomaly is flagged by `identify_mood_anomalies` when a specific day's mood score deviates from your historical baseline beyond a defined sensitivity threshold.