MCP Tools Reference: drivemcp.googleapis.com

Tool: search_files

Search for Drive files using a structured query (syntax: query_term operator values). Combine clauses with and, or, not, and parentheses. String values must be single-quoted; escape embedded quotes as \'.

Query terms & operators:

  • title (ops: contains, =, !=) — file title
  • fullText (ops: contains) — title or body text
  • mimeType (ops: contains, =, !=) — MIME type
  • modifiedTime, viewedByMeTime, createdTime (ops: <=, <, =, !=, >, >=). Use RFC 3339 UTC, e.g., 2012-06-04T12:00:00-08:00. Date types not comparable.
  • parentId (ops: =, !=). Use 'root' for the user's "My Drive".
  • owner (ops: =, !=). Use 'me' for the requesting user.
  • sharedWithMe (ops: =, !=). Values: true or false.

Other operators: and, or, not.

Examples:

  • title contains 'hello' and title contains 'goodbye'
  • modifiedTime > '2024-01-01T00:00:00Z' and (mimeType contains 'image/' or mimeType contains 'video/')
  • parentId = '1234567'
  • fullText contains 'hello'
  • owner = 'test@example.org'
  • sharedWithMe = true
  • owner = 'me' (for files owned by the user)

Use next_page_token to paginate. An empty response means no more results.

The following sample demonstrate how to use curl to invoke the search_files MCP tool.

Curl Request 
curl --location 'https://drivemcp.googleapis.com/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "method": "tools/call",
  "params": {
    "name": "search_files",
    "arguments": {
      // provide these details according to the tool's MCP specification
    }
  },
  "jsonrpc": "2.0",
  "id": 1
}'

Input Schema

Request to search files.

SearchFilesRequest

JSON representation 
{
  "query": string,

  "pageToken": string

  "pageSize": integer

  "excludeContentSnippets": boolean
}
Fields
query

string

The search query.

Union field _page_token.

_page_token can be only one of the following:
pageToken

string

The page token to use for pagination.

Union field _page_size.

_page_size can be only one of the following:
pageSize

integer

The maximum number of files to return in each page.

Union field _exclude_content_snippets.

_exclude_content_snippets can be only one of the following:
excludeContentSnippets

boolean

If true, the content snippet will be excluded from the response.

Output Schema

Response to search files.

SearchFilesResponse

JSON representation 
{
  "files": [
    {
      object (File)
    }
  ],

  "nextPageToken": string
}
Fields
files[]

object (File)

Output only. The list of files.

Union field _next_page_token.

_next_page_token can be only one of the following:
nextPageToken

string

The next page token.

File

JSON representation 
{
  "id": string,
  "title": string,
  "parentId": string,

  "mimeType": string

  "fileSize": string

  "description": string

  "fileExtension": string

  "contentSnippet": string

  "viewUrl": string

  "sharedWithMeTime": string

  "createdTime": string

  "modifiedTime": string

  "viewedByMeTime": string

  "owner": string

  "canAddChildren": boolean
}
Fields
id

string

The id of the file that was fetched.
title

string

The title of the file.
parentId

string

The (optional) id of the parent of the file.

Union field _mime_type.

_mime_type can be only one of the following:
mimeType

string

The mime type of the file.

Union field _file_size.

_file_size can be only one of the following:
fileSize

string (int64 format)

The size in bytes of the file.

Union field _description.

_description can be only one of the following:
description

string

The description of the file.

Union field _file_extension.

_file_extension can be only one of the following:
fileExtension

string

The original file extension of the file, this is only populated for files with content stored in Drive.

Union field _content_snippet.

_content_snippet can be only one of the following:
contentSnippet

string

Generated snippet about the content of the file.

Union field _view_url.

_view_url can be only one of the following:
viewUrl

string

The URL to view the file.

Union field _shared_with_me_time.

_shared_with_me_time can be only one of the following:
sharedWithMeTime

string (Timestamp format)

The time that the file was shared with the requester.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".

Union field _created_time.

_created_time can be only one of the following:
createdTime

string (Timestamp format)

The time that the file was created.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".

Union field _modified_time.

_modified_time can be only one of the following:
modifiedTime

string (Timestamp format)

The most recent time at which the file was modified.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".

Union field _viewed_by_me_time.

_viewed_by_me_time can be only one of the following:
viewedByMeTime

string (Timestamp format)

The most recent time at which the file was viewed by requester.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".

Union field _owner.

_owner can be only one of the following:
owner

string

The email address of the owner of the file.

Union field _can_add_children.

_can_add_children can be only one of the following:
canAddChildren

boolean

Whether the requester can add children to this folder. This is always false for non-folder types.

Timestamp

JSON representation 
{
  "seconds": string,
  "nanos": integer
}
Fields
seconds

string (int64 format)

Represents seconds of UTC time since Unix epoch 1970-01-01T00:00:00Z. Must be between -62135596800 and 253402300799 inclusive (which corresponds to 0001-01-01T00:00:00Z to 9999-12-31T23:59:59Z).
nanos

integer

Non-negative fractions of a second at nanosecond resolution. This field is the nanosecond portion of the duration, not an alternative to seconds. Negative second values with fractions must still have non-negative nanos values that count forward in time. Must be between 0 and 999,999,999 inclusive.

Tool Annotations

Destructive Hint: ❌ | Idempotent Hint: ✅ | Read Only Hint: ✅ | Open World Hint: ❌