Intervals.icu MCP Server

get_activity_streams

Retrieve time-series stream data—power, heart rate, cadence, altitude, distance, and more—for a specific Intervals.icu activity to analyze performance.

Instructions

Get stream data for a specific activity from Intervals.icu

This endpoint returns time-series data for an activity, including metrics like power, heart rate,
cadence, altitude, distance, temperature, and velocity data.

Args:
    activity_id: The Intervals.icu activity ID
    stream_types: Comma-separated list of stream types to retrieve (optional, defaults to all available types)
                 Available types: time, watts, heartrate, cadence, altitude, distance,
                 core_temperature, skin_temperature, velocity_smooth

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "activity_id": "<activity_id>"
    },
    "name": "get_activity_streams"
  }
}

Input Schema

Name	Required	Description	Default
`activity_id`	Yes
`stream_types`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 2, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description must carry the behavioral burden. It does disclose the default behavior (returns all available stream types when unspecified) and enumerates the returned metrics, but says nothing about authentication, rate limits, data volume/size of time-series responses, or units.

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 purpose is front-loaded in the first sentence, and the following sentences add real information (what is returned, valid stream types). The Args block is slightly verbose but every line carries content.

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

Completeness4/5

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

For a two-parameter read tool with an output schema present, the description covers purpose, returned metrics, and the optional filter's valid values and default. Minor gaps remain around data granularity/units and error behavior, but nothing an agent needs to invoke it correctly is missing.

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 coverage is 0%, so the description is the only source of parameter meaning. It fully documents stream_types with the enumerated accepted values and the default-to-all behavior, and identifies activity_id as the Intervals.icu activity ID; only the ID's format is left implicit.

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 specific verb and resource ('Get stream data for a specific activity') and clarifies the payload is time-series data (power, HR, cadence, etc.), which implicitly separates it from siblings like get_activity_details or get_activity_intervals. It does not explicitly name a sibling, so 4 rather than 5.

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

Usage Guidelines3/5

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

The description implies usage (when you need per-sample time-series rather than summary data) through the metric list, but never states when to prefer it over get_activity_details or get_activity_intervals, nor any prerequisites or exclusions.

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