Home / Token cost / Intervals Icu Api

The Intervals Icu Api MCP server costs 48,993 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The Intervals Icu Api MCP server's 146 tool definitions consume 48,993 tokens — 24% of a 200k context window, and 24× the median MCP server (2,069 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #16 of 3,354 measured servers · refreshed every build Method →

What that costs before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 24%
1M WINDOW 4.9%

Corpus context: Intervals Icu Api ranks #16 of 3,354 measured MCP servers by definition cost. The median is 2,069 tokens, p90 is 11,359, and the heaviest (SmartBear MCP) is 137,725 — 69% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Where the 48,993 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 336 tokens per tool.

ToolCategoryTokens% of server
updateAthlete Write 3,797 7.8%
sendMessage Write 2,495 5.1%
createManualActivity Write 2,292 4.7%
updateActivity Write 2,289 4.7%
createEvent Write 1,759 3.6%
updateSettings Write 1,745 3.6%
updateEvent Write 1,736 3.5%
createSettings Write 1,704 3.5%
listAthletePowerCurves Read 1,532 3.1%
listAthletePaceCurves Read 1,529 3.1%
listAthleteHRCurves Read 1,494 3.0%
updateEvents Write 1,430 2.9%
updateSharedEvent Write 1,414 2.9%
createSharedEvent Write 1,402 2.9%
updateFolder Write 949 1.9%
createFolder Write 948 1.9%
updateInterval Write 777 1.6%
updateWellness Write 758 1.5%
updateWellness_1 Write 753 1.5%
listActivityPowerCurves Read 742 1.5%
replaceGear Write 730 1.5%
updateGear Write 720 1.5%
listActivityPaceCurves Read 719 1.5%
createGear Write 710 1.4%
listActivityHRCurves Read 708 1.4%
updatePlanWorkouts Write 441 0.9%
applyPlan Write 431 0.9%
updateWorkout Write 428 0.9%
listEvents Read 427 0.9%
createWorkout Write 427 0.9%
downloadWorkoutForAthlete Read 419 0.9%
downloadWorkout Read 397 0.8%
updateCustomItem Write 353 0.7%
createCustomItem Write 342 0.7%
importWorkoutFile Write 318 0.6%
getAthleteMMPModel Read 287 0.6%
updateReminder Write 245 0.5%
findBestEfforts Read 211 0.4%
createReminder Write 209 0.4%
searchForIntervals Read 206 0.4%
listActivities Read 204 0.4%
listWellnessRecords Read 190 0.4%
deleteEvents Destructive 189 0.4%
createMultipleEvents Write 178 0.4%
uploadActivity Write 177 0.4%
updateAthleteRoute Write 173 0.4%
downloadWorkouts Read 172 0.4%
getAthleteSummary Read 161 0.3%
listActivityPowerCurves_1 Read 149 0.3%
listActivitiesAround Read 136 0.3%
updateWeatherConfig Write 135 0.3%
deleteEvent Destructive 128 0.3%
getActivityMap Read 127 0.3%
downloadActivityFitFiles Read 114 0.2%
getPowerHRCurve Read 109 0.2%
getActivityPowerCurve Read 105 0.2%
getActivityStreams Read 105 0.2%
getActivities Read 103 0.2%
updateAthletePlan Write 103 0.2%
listMessages Read 102 0.2%
getActivityWeatherSummary Read 100 0.2%
searchForActivitiesFull Read 98 0.2%
duplicateEvents Write 97 0.2%
searchForActivities Read 97 0.2%
deleteWorkout Destructive 90 0.2%
downloadActivityGpxFile Read 90 0.2%
getAthleteRoute Read 89 0.2%
downloadActivityFitFile Read 88 0.2%
downloadWorkout_1 Read 87 0.2%
duplicateWorkouts Write 87 0.2%
getActivityPaceCurve Read 84 0.2%
updateCustomItemImage Write 84 0.2%
getIntervalStats Read 82 0.2%
checkMerge Read 80 0.2%
getSettings_1 Read 80 0.2%
getPowerVsHR Read 79 0.2%
uploadWellness Write 79 0.2%
getActivityHRCurve Read 78 0.2%
listPaceDistancesForSport Read 78 0.2%
deleteReminder Destructive 77 0.2%
getHRHistogram Read 76 0.2%
applyToActivities Write 76 0.2%
updateIntervals Write 76 0.2%
getPowerHistogram Read 75 0.2%
listActivityMessages Read 75 0.2%
uploadActivityStreamsCSV Write 75 0.2%
listFolderSharedWith Read 74 0.2%
updateSettingsMulti Write 74 0.2%
updateFolderSharedWith Write 73 0.1%
getRecord Read 72 0.1%
getSettings Read 72 0.1%
splitInterval Write 72 0.1%
markEventAsDone Write 72 0.1%
showEvent Read 71 0.1%
updateLastSeenMessageId Write 71 0.1%
deleteFolder Destructive 70 0.1%
listGear Read 70 0.1%
listMatchingActivities Read 69 0.1%
calcDistanceEtc Read 67 0.1%
getActivity Read 67 0.1%
createMultipleWorkouts Write 67 0.1%
sendActivityMessage Write 67 0.1%
deleteCustomItem Destructive 66 0.1%
deleteGear Destructive 66 0.1%
deleteSettings Destructive 66 0.1%
getCustomItem Read 66 0.1%
listTags_1 Read 66 0.1%
showWorkout Read 66 0.1%
applyCurrentPlanChanges Write 66 0.1%
listFitnessModelEvents Read 65 0.1%
deleteMessage Destructive 64 0.1%
listTags Read 64 0.1%
listTags_2 Read 64 0.1%
deleteEventsBulk Destructive 63 0.1%
updateWellnessBulk Write 63 0.1%
createMultipleManualActivities Write 62 0.1%
deleteSharedEvent Destructive 61 0.1%
downloadActivityFile Read 61 0.1%
getSharedEvent Read 61 0.1%
listCustomItems Read 61 0.1%
getAthlete Read 60 0.1%
getHRTrainingLoadModel Read 60 0.1%
listAthleteRoutes Read 60 0.1%
listChats Read 60 0.1%
listFolders Read 60 0.1%
listSettings Read 60 0.1%
listWorkouts Read 60 0.1%
getActivityPowerSpikeModel Read 59 0.1%
getAthleteTrainingPlan Read 59 0.1%
getTimeAtHR Read 59 0.1%
getWeatherConfig Read 58 0.1%
updateActivityStreams Write 58 0.1%
getGapHistogram Read 57 0.1%
downloadActivitiesAsCSV Read 56 0.1%
getAthleteProfile Read 56 0.1%
getPaceHistogram Read 56 0.1%
updateCustomItemIndexes Write 56 0.1%
showChat Read 55 0.1%
getActivitySegments Read 54 0.1%
getForecast Read 54 0.1%
deleteActivity Destructive 53 0.1%
getIntervals Read 53 0.1%
deleteIntervals Destructive 52 0.1%
disconnectApp Write 31 0.1%
updateAthletePlans Write 31 0.1%
listPaceDistances Read 27 0.1%

Your agent uses a handful of these tools. It pays for all 146.

You don't need all 146 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Intervals Icu Api: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scopeDefinition costReduction
All 146 tools (no gateway) 48,993 tokens
3 granted tools ~1,007 tokens −98%
5 granted tools ~1,678 tokens −97%
10 granted tools ~3,356 tokens −93%

The risk dividend: 13 of these 146 tools are critical-risk (destructive or financial) and cost 1,045 tokens (2% of the definition load). Block them — the recommended starter policy — and you reclaim that context before tuning anything else.

  1. Create a free account and register Intervals Icu Api — nothing to install.
  2. Grant only the tools you use — ungranted definitions never enter the context window.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CUT INTERVALS ICU API TOKEN COST →

Instant setup, no code required.

Intervals Icu Api token-cost questions.

How many tokens does the Intervals Icu Api MCP server use?+

Its 146 tool definitions total 48,993 tokens — 24% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does Intervals Icu Api consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce Intervals Icu Api's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Intervals Icu Api to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 1,007 tokens, a 98% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

How these numbers were measured.

01
Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02
Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03
Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 06-07-2026 from the PolicyLayer scan database over all 146 catalogued Intervals Icu Api tools. Counts refresh with every site build.

Expose only the tools you use — the rest never enter your context.

A PolicyLayer grant scopes Intervals Icu Api to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.