Skip to main content
Glama
Softeria

Microsoft 365 MCP Server

by Softeria

search-onedrive-files

search-onedrive-files
Read-only

Search OneDrive files by name, metadata, or content. Filter results by folder drive or shared items, and get matching file IDs, names, URLs, sizes, and timestamps to locate files quickly.

Instructions

Search the hierarchy of items for items matching a query. You can search within a folder hierarchy, a whole drive, or files shared with the current user.

đź’ˇ TIP: Searches for files in a drive by name or content. The q parameter searches file names, metadata, and file content. Returns matching driveItems with id, name, webUrl, size, lastModifiedDateTime. Use list-drives first to get the drive-id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesValue for the 'q' path segment.
topNoPage 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.
skipNoItems to skip for pagination. Not supported with $search.
countNoSet true to enable advanced query mode (ConsistencyLevel: eventual). Required for complex $filter on flag/flagStatus or contains().
expandNoNavigation 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.
filterNoOData filter expression. Add $count=true for advanced filters (flag/flagStatus, contains()). Cannot combine with $search.
searchNoKQL search query in one pair of double quotes; directory (users/groups) instead quotes each clause with no outer pair. Cannot combine with $filter.
selectNoComma-separated fields to return, e.g. id,subject,from,receivedDateTime
driveIdYesValue for the 'driveId' path segment. Pass it under the name 'driveId', not as 'id'. Use the 'id' field of the drive object as returned by Microsoft Graph.
orderbyNoSort expression, e.g. receivedDateTime desc
skiptokenNoNext page: the @odata.nextLink from the previous response. Keep the other arguments the same.
fetchAllPagesNoFollow @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.
includeHeadersNoInclude response headers (including ETag) in the response metadata
excludeResponseNoExclude the full response body and only return success or failure indication

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.154.2
    • 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"
  2. Changed1 schema field changedv0.154.0
    • 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."
  3. Changed2 schema fields changedv0.153.0
    • 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"
      +}
  4. Changed3 schema fields changedv0.134.4
    • changedInput schema / properties / driveId / description
      Previous value: -"Path parameter: driveId"New value: +"Value for the 'driveId' path segment. Pass it under the name 'driveId', not as 'id'. Use the 'id' field of the drive object as returned by Microsoft Graph."
    • changedInput schema / properties / expand / description
      Previous value: -"Expand related entities"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\", and an unsupported value may be ignored rather than reported. Request ordinary fields with $select instead."
    • changedInput schema / properties / q / description
      Previous value: -"Path parameter: q"New value: +"Value for the 'q' path segment."
  5. Addedv0.131.2
  6. Removedv0.131.2
  7. Addedv0.114.0
  8. Removedv0.112.2
  9. Addedv0.110.0
  10. Removedv0.108.0
  11. Addedv0.96.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, so the safety profile is covered. The description adds behavioral detail by stating the q parameter searches file names, metadata, and content, and that the response includes id, name, webUrl, size, lastModifiedDateTime. It does not contradict the annotations, and it adds useful context about what the search affects and returns.

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

Conciseness5/5

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

The description is two short sentences plus a tip, with the main purpose front-loaded. Every sentence earns its place: purpose, scope, search semantics, return fields, and prerequisite. No filler or repetition.

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 read-only search tool with 14 parameters, the schema already documents parameters thoroughly. The description covers the essential usage context: what can be searched, what is returned, and how to obtain the required driveId. The absence of an output schema is mitigated by listing return fields, and the read-only nature is already annotated. This is sufficiently complete for an agent to call the tool correctly.

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?

Although the schema covers all 14 parameters (100% coverage), the description enriches the otherwise terse q parameter schema ('Value for the q path segment') by explaining it searches file names, metadata, and content. It also reinforces the driveId prerequisite. This adds meaning beyond the schema baseline of 3, so a 4 is appropriate.

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?

The description opens with a specific action and resource: 'Search the hierarchy of items for items matching a query.' It further clarifies scope (folder hierarchy, whole drive, shared files) and notes the q parameter searches file names, metadata, and content. This clearly distinguishes it from sibling listing tools such as list-folder-files or get-drive-item.

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

Usage Guidelines4/5

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

The description gives practical guidance in the TIP: 'Use list-drives first to get the drive-id,' establishing a prerequisite. It also explains the search semantics (by name or content) and returned fields, which tells the agent when this tool is appropriate. It lacks an explicit 'when not to use' or alternative comparison, but the context is clear.

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

Deploy Server

Other Tools