Intervals.icu MCP Server

Get activity time series

get_activity_streams

Read-onlyIdempotent

Retrieve downsampled second-by-second activity data (heart rate, pace, cadence, altitude, power) to analyze pacing, HR drift, and effort changes over time. Optionally include GPS coordinates.

Instructions

Get second-by-second data of one activity (heart rate, pace/speed, cadence, altitude, distance, power), downsampled to a compact table: each row averages a time window. Use it to analyse pacing, HR drift or how effort changed during the session. GPS coordinates are only included when "latlng" is requested explicitly.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Activity id, e.g. "i123456789" (from list_activities or search_activities).
`end`	No	Only up to this elapsed time (seconds or "m:ss").
`start`	No	Only from this elapsed time (seconds or "m:ss").
`types`	No	Stream types. Default: distance, heartrate, velocity_smooth, cadence, altitude, watts. Others include temp, respiration, grade_smooth, latlng (GPS).
`max_points`	No	Maximum rows (default 120).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	Yes
`columns`	Yes
`rows_count`	Yes
`activity_id`	Yes
`source_points`	Yes
`seconds_per_row`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.0.0Sep 26, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the readOnly/idempotent annotations, it discloses two non-obvious behaviors: data is downsampled into averaged time windows, and GPS coordinates are returned only when 'latlng' is explicitly requested. This materially shapes how an agent interprets results. No contradiction with annotations.

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?

Three sentences, each earning its place: what it returns, when to use it, and an important caveat. Main purpose is front-loaded.

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?

With a full input schema, output schema, and safety annotations, the description covers the remaining contextual needs: temporal resolution, aggregation, and the GPS caveat. No critical information is missing for an agent to select and call the tool.

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

Parameters4/5

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

Schema already describes all five parameters, so baseline is 3; the description adds semantic value by explaining the aggregation behavior behind max_points and the conditional inclusion of GPS behind types, which are not inferable from the schema alone.

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

Purpose4/5

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

States a clear verb and resource: retrieve second-by-second stream data for one activity (HR, pace, cadence, etc.). It implicitly differentiates from list/summary siblings, but does not explicitly name an alternative tool, so it stops short of full sibling differentiation.

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?

Gives concrete use cases ('analyse pacing, HR drift or how effort changed during the session'), making the intended context clear. It does not say when not to use it or name alternatives such as get_activity_histogram, so exclusion guidance is missing.

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