Garmin MCP

garmin_viz

Generate visual charts from Garmin Connect health and activity data. Supports line, bar, scatter, histogram, pie, heatmap, and multi-line charts to analyze steps, sleep, stress, and more.

Instructions

Render a chart and return the image inline (displayed by Claude Desktop) plus the saved file path.

chart_type: "line", "bar", "scatter", "histogram", "pie", "heatmap", or "multi_line".

Common params (used by most types): x: x-axis values or labels. y: y-axis values (for histogram, pass the data here). title, x_label, y_label: chart labels.

Type-specific params: histogram: bins (default 20). heatmap: matrix (2-D list), x_labels, y_labels. multi_line: y_series (list of y-value lists), series_labels.

Examples: Line: chart_type="line", x=["Mon","Tue",...], y=[8000,9200,...] Bar: chart_type="bar", x=["running","strength"], y=[5,3] Scatter: chart_type="scatter", x=[steps...], y=[sleep_scores...] Histogram: chart_type="histogram", y=[hrv_values...] Pie: chart_type="pie", x=["running","cycling"], y=[120,80] Heatmap: chart_type="heatmap", matrix=[[...],[...]], x_labels=["Mon",...], y_labels=["Wk1",...] Multi-line: chart_type="multi_line", x=[dates...], y_series=[[rhr...],[stress...]], series_labels=["RHR","Stress"]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No
`y`	No
`bins`	No
`title`	No
`matrix`	No
`x_label`	No
`y_label`	No
`x_labels`	No
`y_labels`	No
`y_series`	No
`chart_type`	Yes
`series_labels`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 6, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It explicitly says the tool renders a chart, returns the image inline, and provides a saved file path—covering the key behavioral outcomes. It does not discuss side effects like file overwriting, but for a visualization tool this is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but every section earns its place: purpose first, then common params, type-specific params, and concrete examples. The grouped, scannable structure makes it easy for an agent to find the relevant chart-type details without wading through irrelevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 12 parameters and 7 chart types, the description is remarkably complete: it covers all parameter combinations, provides default behavior for bins, and gives example calls for every chart type. The output schema covers return-value structure, so no critical invocation detail is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate fully, and it does. It documents every parameter, distinguishes common from type-specific params, and clarifies how x, y, matrix, y_series, and labels apply per chart type. The examples further resolve ambiguity that the schema alone cannot.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Render a chart') and resource, and clarifies the output format (inline image plus saved file path). It is clearly distinct from sibling data-retrieval tools like garmin_data or garmin_stats, so an agent can tell exactly what this tool is for.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool—whenever a chart image is needed—and explains the supported chart types and their parameter requirements. It does not explicitly name alternatives or exclusion conditions, but the purpose is distinct enough among siblings that usage is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server