Microsoft 365 MCP Server

list-drives

list-drives

Read-only

Retrieve the list of Drive resources available for a target User, Group, or Site.

Instructions

Retrieve the list of Drive resources available for a target User, Group, or Site.

Input Schema

Name	Required	Description
`top`	No	Page size (Graph $top). Start small (e.g. 5–15) so responses fit the model context; raise only if needed. Use $select to return fewer fields per item. For more rows, use @odata.nextLink from the response instead of a very large $top.
`skip`	No	Items to skip for pagination. Not supported with $search.
`count`	No	Set true to enable advanced query mode (ConsistencyLevel: eventual). Required for complex $filter on flag/flagStatus or contains(). The response then includes @odata.count, the total for the filtered collection, which can exceed the items returned when fetchAllPages hits its page/item cap.
`expand`	No	Navigation properties to inline, e.g. attachments on a message or event. Only navigation properties can be expanded: expanding a non-navigation property such as a message body fails with "Parsing OData Select and Expand failed". Request ordinary fields with $select instead. Some APIs accept only one relationship per request, so prefer a single value. Some relationships support nested selection, e.g. children($select=id,name).
`filter`	No	OData filter expression. Add $count=true for advanced filters (flag/flagStatus, contains()). Cannot combine with $search.
`search`	No	KQL search query in one pair of double quotes; directory (users/groups) instead quotes each clause with no outer pair. Cannot combine with $filter.
`select`	No	Comma-separated fields to return, e.g. id,subject,from,receivedDateTime
`orderby`	No	Sort expression, e.g. receivedDateTime desc
`skiptoken`	No	Next page: the @odata.nextLink from the previous response. Keep the other arguments the same.
`fetchAllPages`	No	Follow @odata.nextLink and merge up to 100 pages into one response. Can return enormous payloads—only when the user explicitly needs a full export. Prefer a small $top first, then paginate or narrow with $filter/$search.
`includeHeaders`	No	Include response headers (including ETag) in the response metadata
`excludeResponse`	No	Exclude the full response body and only return success or failure indication

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.166.0Oct 14, 2026

changedInput schema / properties / count / description

Previous value: -"Set true to enable advanced query mode (ConsistencyLevel: eventual). Required for complex $filter on flag/flagStatus or contains()."New value: +"Set true to enable advanced query mode (ConsistencyLevel: eventual). Required for complex $filter on flag/flagStatus or contains(). The response then includes @odata.count, the total for the filtered collection, which can exceed the items returned when fetchAllPages hits its page/item cap."

changedInput schema / properties / expand / description

Previous value: -"Navigation properties to inline, e.g. attachments on a message or event. Only navigation properties can be expanded: expanding a non-navigation property such as a message body fails with \"Parsing OData Select and Expand failed\", and an unsupported value may be ignored rather than reported. Request ordinary fields with $select instead."New value: +"Navigation properties to inline, e.g. attachments on a message or event. Only navigation properties can be expanded: expanding a non-navigation property such as a message body fails with \"Parsing OData Select and Expand failed\". Request ordinary fields with $select instead. Some APIs accept only one relationship per request, so prefer a single value. Some relationships support nested selection, e.g. children($select=id,name)."

Changed11 schema fields changedv0.154.2Sep 17, 2026

addedInput schema / properties / expand / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / expand / items
```
Removed value: -{
-  "type": "string"
-}
```
removedInput schema / properties / expand / type
```
Removed value: -"array"
```

addedInput schema / properties / orderby / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / orderby / type
```
Removed value: -"string"
```

addedInput schema / properties / select / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / select / type
```
Removed value: -"string"
```
addedInput schema / properties / skip / minimum
```
Added value: +0
```

changedInput schema / properties / skip / type

Previous value: -"number"New value: +"integer"

addedInput schema / properties / top / minimum
```
Added value: +0
```

changedInput schema / properties / top / type

Previous value: -"number"New value: +"integer"

Changed1 schema field changedv0.154.0Sep 12, 2026

changedInput schema / properties / skiptoken / description

Previous value: -"Opaque cursor for the next page, taken from the previous response. Copy the $skiptoken value out of @odata.nextLink (or paste the whole nextLink URL — the token is extracted from it) and resend it with the SAME $filter/$select/$expand/$top as the first call. Use this to walk pages one at a time instead of fetchAllPages. Omit it for the first page."New value: +"Next page: the @odata.nextLink from the previous response. Keep the other arguments the same."

Changed2 schema fields changedv0.153.0Sep 12, 2026

changedInput schema / properties / search / description

Previous value: -"KQL search query — wrap value in double quotes. Cannot combine with $filter."New value: +"KQL search query in one pair of double quotes; directory (users/groups) instead quotes each clause with no outer pair. Cannot combine with $filter."

addedInput schema / properties / skiptoken

Added value: +{
+  "description": "Opaque cursor for the next page, taken from the previous response. Copy the $skiptoken value out of @odata.nextLink (or paste the whole nextLink URL — the token is extracted from it) and resend it with the SAME $filter/$select/$expand/$top as the first call. Use this to walk pages one at a time instead of fetchAllPages. Omit it for the first page.",
+  "type": "string"
+}

Addedv0.134.4Jul 28, 2026
Removedv0.131.2Jul 18, 2026
Addedv0.114.0May 28, 2026
Removedv0.112.2May 22, 2026
Addedv0.110.0May 18, 2026
Removedv0.108.0May 15, 2026

Changed16 schema fields changedv0.96.0May 4, 2026

changedInput schema / properties / count / description

Previous value: -"Include count of items"New value: +"Set true to enable advanced query mode (ConsistencyLevel: eventual). Required for complex $filter on flag/flagStatus or contains()."

changedInput schema / properties / fetchAllPages / description

Previous value: -"Automatically fetch all pages of results"New value: +"Follow @odata.nextLink and merge up to 100 pages into one response. Can return enormous payloads—only when the user explicitly needs a full export. Prefer a small $top first, then paginate or narrow with $filter/$search."

changedInput schema / properties / filter / description

Previous value: -"Filter items by property values"New value: +"OData filter expression. Add $count=true for advanced filters (flag/flagStatus, contains()). Cannot combine with $search."

changedInput schema / properties / orderby / description

Previous value: -"Order items by property values"New value: +"Sort expression, e.g. receivedDateTime desc"

removedInput schema / properties / orderby / items
```
Removed value: -{
-  "type": "string"
-}
```
changedInput schema / properties / orderby / type
```
Previous value: -"array"New value: +"string"
```

changedInput schema / properties / search / description

Previous value: -"Search items by search phrases"New value: +"KQL search query — wrap value in double quotes. Cannot combine with $filter."

changedInput schema / properties / select / description

Previous value: -"Select properties to be returned"New value: +"Comma-separated fields to return, e.g. id,subject,from,receivedDateTime"

removedInput schema / properties / select / items
```
Removed value: -{
-  "type": "string"
-}
```

changedInput schema / properties / select / type

Previous value: -"array"New value: +"string"

changedInput schema / properties / skip / description

Previous value: -"Skip the first n items"New value: +"Items to skip for pagination. Not supported with $search."

removedInput schema / properties / skip / minimum
```
Removed value: -0
```

changedInput schema / properties / skip / type

Previous value: -"integer"New value: +"number"

changedInput schema / properties / top / description

Previous value: -"Show only the first n items"New value: +"Page size (Graph $top). Start small (e.g. 5–15) so responses fit the model context; raise only if needed. Use $select to return fewer fields per item. For more rows, use @odata.nextLink from the response instead of a very large $top."

removedInput schema / properties / top / minimum
```
Removed value: -0
```

changedInput schema / properties / top / type

Previous value: -"integer"New value: +"number"

First observedv0.31.0Jan 27, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds only the scoping notion of User/Group/Site, with no mention of pagination, auth requirements, or result shape; it neither contradicts nor enriches the annotations much, so a minimum-viable 3 is warranted.

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?

A single, front-loaded sentence with no wasted words. It is appropriately sized, though the 'target User, Group, or Site' clause introduces ambiguity that a more precise phrasing would avoid.

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?

With no output schema, the description should clarify what a returned 'Drive resource' looks like, but it does not. The 12 parameters are fully covered by the schema and annotations cover safety, so the core gaps are the unexplained scoping target and the unspecified return shape.

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 100%, and all 12 parameters (top, skip, count, filter, search, skiptoken, fetchAllPages, etc.) are thoroughly documented in the schema itself. The description adds no parameter-level detail, so the baseline 3 applies since the schema carries the full burden.

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 (Retrieve/list) and resource (Drive resources), and scopes it to a target User, Group, or Site, which distinguishes it from siblings like get-drive-root-item or list-folder-files. However, the described 'target' has no corresponding parameter in the schema, so the scoping claim is unclear and only partially helps an agent differentiate.

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 no when-to-use guidance and never names alternatives such as get-drive-root-item, search-onedrive-files, get-drive-delta, or list-folder-files, despite many drive-related siblings. An agent must infer usage from the name alone.

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

Deploy Server

list-drives

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools