Intervals.icu MCP Server

Overview Schema Source Related Servers Discussions Admin

get_activity_streams

Retrieve activity streams from Intervals.icu by sample index using a bounded preview or custom range. Choose stream types, detect truncation, and use snapshot IDs to continue consistently with larger transfers.

Instructions

Read activity streams by sample index with bounded preview or range.

range uses half-open sample indices [start_index, end_index); those indices are not elapsed seconds and a single range is limited to 10,000 samples. Use export_activity_data plus get_artifact_chunk for a larger complete transfer. preview returns all samples for short arrays and only the first and last five samples for longer arrays, reporting truncation only when samples were omitted. Missing stream types, missing/null primary arrays, ambiguous or unavailable time axes, and unequal lengths are explicit warnings. Duplicate and custom upstream streams are retained in order, and no primary data array is invented for a data2-only stream. The 1/min cadence unit is a display hint when the source did not declare a unit; Ride commonly means revolutions per minute, while running conventions depend on the device and upstream field, with no x2 conversion. alignment.quality describes array-length alignment only; it does not assert monotonic, regular, or non-null time values. The snapshot hashes the returned payload for this selection, so a continuation must keep the same activity and stream_types.

Respiratory fields: tidal_volume = VT (volume per breath, not VT1/VT2), tidal_volume_min = VE (minute ventilation), respiration = BR (breaths/min). When sourced from Tymewear, VT uses relative i.u. and VE relative vol/min, not calibrated liters. Do not divide VT by 100 or 1000. The response adds conditional documentation in provenance.respiratory_interpretation; original samples and source unit labels are preserved. Use get_metric_definitions and get_custom_items to check mappings and units.

Input Schema

TableJSON Schema

Name	Required	Default
`mode`	No	preview
`api_key`	No
`end_index`	No
`activity_id`	Yes
`start_index`	No
`stream_types`	No
`expected_snapshot_id`	No

Output Schema

TableJSON Schema

Name	Required	Default
`data`	Yes
`error`	No
`query`	No
`source`	Yes
`status`	Yes
`coverage`	Yes
`warnings`	No
`pagination`	No
`request_id`	No
`schema_version`	No	1.0

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden, and it delivers extensively: half-open index semantics, index-not-seconds clarification, preview truncation rules, explicit warning conditions, duplicate/custom stream retention, no invented data array, the 1/min display-hint nuance, alignment.quality limits, snapshot-continuation requirements, and respiratory unit conventions. This is far beyond what annotations would typically supply.

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

Conciseness4/5

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

The description is front-loaded with the core scoping statement and each subsequent sentence carries substantive behavioral information rather than filler. It is long and somewhat wall-of-text in structure, which hurts scannability, but nearly every sentence earns its place given the tool's complexity and absence of annotations.

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 the tool's complexity—7 parameters, zero schema descriptions, no annotations—the description is remarkably complete. An output schema exists, so return-value format needs no explanation, and the description covers modes, edge cases, warnings, unit semantics, snapshot continuation, and respiratory interpretation. Nothing an agent needs to call it correctly 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, and it does: mode (preview/range behavior), start_index/end_index (half-open, not seconds, 10,000 limit), stream_types (warnings, duplicates, data2-only streams), and expected_snapshot_id (snapshot hashing and continuation requirements) all receive deep meaning beyond the schema. Only api_key is left to inference, which is minor given the exceptional compensation elsewhere.

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?

Opens with a specific verb+resource statement: 'Read activity streams by sample index with bounded preview or range.' It distinguishes itself from siblings by explicitly positioning export_activity_data plus get_artifact_chunk as the alternative for larger transfers, and by naming get_metric_definitions and get_custom_items for unit/mapping checks. An agent can tell exactly what this tool does versus its siblings.

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

Usage Guidelines5/5

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

Provides explicit selection criteria: preview versus range mode, the 10,000-sample limit, and an explicit instruction to use export_activity_data plus get_artifact_chunk for a larger complete transfer. It also directs the agent to get_metric_definitions and get_custom_items when checking mappings and units. This is rare, concrete routing guidance with named alternatives.

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