Oura MCP

Oura Daily Sleep

oura_list_daily_sleep

Read-onlyIdempotent

Fetch daily sleep score summaries from Oura Ring data for a specified date range. Use this to retrieve sleep metrics for tracking, analysis, and reporting.

Instructions

List daily Oura sleep score summaries. Requires daily or sleep data access granted by the user. Not medical advice.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`after`	No	Only return Oura records after this time. Converted to an Oura start_date.
`limit`	No	Maximum number of records returned by this call, kept from the OLDEST end of the window. Oura v2 serves collections oldest-first, has no sort parameter and no page-size parameter, so limit=1 returns the OLDEST record in the window, never the newest. This domain has no latest-record shortcut resource (only daily readiness has one), so to reach the newest record here, narrow the window with after/before until the response comes back with truncated=false and has_more=false: records are oldest-first, so the LAST one is then the newest that exists in that window. The cap is applied locally after fetching and also stops cursor pagination once it is reached; when it dropped records, truncated is true and has_more is true. If truncated is true, raise limit or set all_pages — do not follow a cursor, because next_token is omitted whenever resuming would skip dropped records.
`before`	No	Only return Oura records before this time. Converted to an Oura end_date.
`all_pages`	No	When true, follow the Oura next_token cursor up to max_pages in this one call. Resume later by passing the returned next_token with the same after/before window.
`max_pages`	No	Maximum upstream Oura pages to fetch in this call when all_pages is true. A runaway guard, not an Oura page index.
`next_token`	No	Opaque Oura v2 cursor from a previous collection response. Pass it back unchanged with the same after/before window to resume. Oura has no integer page index and no page-size parameter; do not invent or increment a page number.
`privacy_mode`	No	Optional per-call privacy override. Defaults to OURA_PRIVACY_MODE or structured. raw returns upstream Oura JSON. summary minimizes sensitive health and profile details.
`response_format`	No		markdown
`explicit_user_intent`	No	Required true when privacy_mode=raw (agent escalation of redaction).

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes
`records`	Yes
`endpoint`	Yes
`has_more`	Yes	True when more records exist beyond this response, either upstream (a resumable next_token) or because the limit cap dropped records (truncated). If truncated is true, raise limit or set all_pages; if next_token is present, pass it back.
`truncated`	Yes	True when the limit cap dropped records that had already been fetched. Raise limit or set all_pages (or narrow after/before) to see them. next_token is omitted in this case so a resume cannot skip those rows.
`next_token`	No	Opaque Oura v2 cursor to resume from. Pass this back as input next_token with the same after/before window. Present only when more records exist upstream AND this call did not locally drop fetched records (truncated is false). When truncated is true, next_token is omitted: raise limit or set all_pages instead of following a cursor, which would skip the dropped records. Never increment a page number.
`privacy_mode`	Yes
`pages_fetched`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.7.2Aug 30, 2026

changedInput schema / properties / after / pattern

Previous value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"New value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"

changedInput schema / properties / all_pages / description

Previous value: -"Fetch multiple pages up to max_pages."New value: +"When true, follow the Oura next_token cursor up to max_pages in this one call. Resume later by passing the returned next_token with the same after/before window."

changedInput schema / properties / before / pattern

Previous value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"New value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"

changedInput schema / properties / limit / description

Previous value: -"Local page-size hint used for pagination safety."New value: +"Maximum number of records returned by this call, kept from the OLDEST end of the window. Oura v2 serves collections oldest-first, has no sort parameter and no page-size parameter, so limit=1 returns the OLDEST record in the window, never the newest. This domain has no latest-record shortcut resource (only daily readiness has one), so to reach the newest record here, narrow the window with after/before until the response comes back with truncated=false and has_more=false: records are oldest-first, so the LAST one is then the newest that exists in that window. The cap is applied locally after fetching and also stops cursor pagination once it is reached; when it dropped records, truncated is true and has_more is true. If truncated is true, raise limit or set all_pages — do not follow a cursor, because next_token is omitted whenever resuming would skip dropped records."

changedInput schema / properties / max_pages / description

Previous value: -"Maximum pages to fetch when all_pages is true."New value: +"Maximum upstream Oura pages to fetch in this call when all_pages is true. A runaway guard, not an Oura page index."

addedInput schema / properties / next_token

Added value: +{
+  "description": "Opaque Oura v2 cursor from a previous collection response. Pass it back unchanged with the same after/before window to resume. Oura has no integer page index and no page-size parameter; do not invent or increment a page number.",
+  "maxLength": 4096,
+  "minLength": 1,
+  "type": "string"
+}

removedInput schema / properties / page

Removed value: -{
-  "default": 1,
-  "description": "Oura page number.",
-  "maximum": 9007199254740991,
-  "minimum": 1,
-  "type": "integer"
-}

addedOutput schema / properties / has_more / description

Added value: +"True when more records exist beyond this response, either upstream (a resumable next_token) or because the limit cap dropped records (truncated). If truncated is true, raise limit or set all_pages; if next_token is present, pass it back."

removedOutput schema / properties / next_page

Removed value: -{
-  "exclusiveMinimum": 0,
-  "maximum": 9007199254740991,
-  "type": "integer"
-}

addedOutput schema / properties / next_token

Added value: +{
+  "description": "Opaque Oura v2 cursor to resume from. Pass this back as input next_token with the same after/before window. Present only when more records exist upstream AND this call did not locally drop fetched records (truncated is false). When truncated is true, next_token is omitted: raise limit or set all_pages instead of following a cursor, which would skip the dropped records. Never increment a page number.",
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when the limit cap dropped records that had already been fetched. Raise limit or set all_pages (or narrow after/before) to see them. next_token is omitted in this case so a resume cannot skip those rows.",
+  "type": "boolean"
+}

changedOutput schema / required

Previous value: -[
-  "endpoint",
-  "privacy_mode",
-  "count",
-  "records",
-  "has_more",
-  "pages_fetched"
-]New value: +[
+  "endpoint",
+  "privacy_mode",
+  "count",
+  "records",
+  "has_more",
+  "truncated",
+  "pages_fetched"
+]

Addedv0.4.11Jul 30, 2026
Removedv0.4.7Jul 17, 2026
First observedv0.4.6Jun 4, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it discloses that the user must have granted daily or sleep data access. It does not mention pagination or privacy nuances, but those are documented in the schema.

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 definition is short and front-loads the main purpose in the first sentence. The access requirement is useful; however, 'Not medical advice.' does little to help selection or invocation and does not earn its place, preventing a perfect score.

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

Completeness3/5

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

The tool has nine parameters, pagination behavior, privacy controls, and many siblings, so a richer description would normally be expected. However, the input schema is very detailed and an output schema exists, which offsets much of the complexity. The main contextual gap is lack of usage differentiation among the many related Oura tools.

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

Parameters3/5

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

Schema description coverage is high (89%), so the schema already explains the parameters in detail. The tool description itself adds no parameter-specific meaning beyond the notion of 'daily sleep score summaries,' which matches the baseline of 3 for schema-heavy tools.

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?

The description states a clear verb and resource: 'List daily Oura sleep score summaries.' This is specific enough to indicate the tool's basic purpose, but it does not explicitly distinguish itself from sibling tools like oura_list_sleep or oura_list_daily_readiness, so it falls short of full differentiation.

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

Usage Guidelines2/5

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

The description gives an access prerequisite and a medical disclaimer but provides no guidance on when to choose this tool over siblings such as oura_list_sleep, oura_list_daily_readiness, or other Oura data tools. An agent is left to infer the appropriate selection context.

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