An MCP (Model Context Protocol) server for reading Google Docs, Sheets, and Slides.
Read-only access to Google Docs, Sheets, and Slides via MCP tools.
- get_document_metadata - Get document metadata (title, word count, element counts)
- get_document_content - Get structured content (headings, paragraphs, images, tables)
- get_document_text - Get all text as a single plain text string
- get_document_paragraphs - Get text organized by paragraphs
- get_spreadsheet_metadata - Get spreadsheet metadata (title, sheet count, locale, time zone)
- list_sheets - List all sheets with their properties
- get_sheet_values - Get cell values from a specific range
- get_sheet_data - Get all data from a specific sheet
- get_multiple_ranges - Batch get values from multiple ranges
- get_presentation - Get presentation metadata (title, slide count, locale, revision ID)
- list_slides - List all slides with titles and element counts
- get_slide - Get slide content and element details by index or object ID
- get_slide_notes - Get speaker notes by slide index or object ID
- get_presentation_content - Get all slides' text and images in one call (ideal for AI)
This server is built on omniskill, making its Google Docs, Sheets, and Slides skills composable building blocks that can be reused in multi-service MCP servers.
The skills in this repository can be imported and combined with other skills:
import (
"github.com/plexusone/mcp-google/skills/docs"
"github.com/plexusone/mcp-google/skills/sheets"
"github.com/plexusone/mcp-google/skills/slides"
runtime "github.com/plexusone/omniskill/mcp/server"
)
// Create runtime
rt := runtime.New(&mcp.Implementation{
Name: "work-mcp-server",
Version: "v1.0.0",
}, nil)
// Add Google skills
docsSkill := docs.New(googleHTTPClient)
docsSkill.Init(ctx)
rt.RegisterSkill(docsSkill)
sheetsSkill := sheets.New(googleHTTPClient)
sheetsSkill.Init(ctx)
rt.RegisterSkill(sheetsSkill)
slidesSkill := slides.New(googleHTTPClient)
slidesSkill.Init(ctx)
rt.RegisterSkill(slidesSkill)
// Add other skills (Slack, Jira, GitHub, etc.)
rt.RegisterSkill(slackSkill)
rt.RegisterSkill(jiraSkill)
// Run server
rt.ServeStdio(ctx)This enables building unified MCP servers that combine multiple services while keeping each service's implementation modular and maintainable.
- Go 1.24+
- Google Cloud service account with Docs, Sheets, and Slides API access
go install github.com/plexusone/mcp-google/cmd/mcp-google@latestOr build from source:
git clone https://github.com/plexusone/mcp-google.git
cd mcp-google
go build ./cmd/mcp-google- Go to the Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Docs API, Google Sheets API, and Google Slides API
- Create a service account with no special roles
- Download the JSON credentials file
Share any documents, spreadsheets, or presentations you want to access with the service account's email address (found in the credentials JSON as client_email).
Use a standard Google Cloud service account JSON file:
mcp-google --credentials /path/to/service-account.jsonOr using an environment variable:
export GOOGLE_CREDENTIALS_FILE=/path/to/service-account.json
mcp-googleUse a goauth CredentialsSet file, which can store multiple credentials:
mcp-google --goauth-credentials-file /path/to/credentials.json --goauth-credentials-account myaccountOr using environment variables:
export GOAUTH_CREDENTIALS_FILE=/path/to/credentials.json
export GOAUTH_CREDENTIALS_ACCOUNT=myaccount
mcp-googleThe CredentialsSet entry should be of type gcpsa with appropriate scopes:
{
"credentials": {
"myaccount": {
"type": "gcpsa",
"gcpsa": {
"gcpCredentials": {
"type": "service_account",
"project_id": "...",
"private_key_id": "...",
"private_key": "...",
"client_email": "...",
"client_id": "..."
},
"scopes": [
"https://www.googleapis.com/auth/documents.readonly",
"https://www.googleapis.com/auth/spreadsheets.readonly",
"https://www.googleapis.com/auth/presentations.readonly",
"https://www.googleapis.com/auth/drive.readonly"
]
}
}
}
}Use omnitoken with omnivault-desktop for secure credential storage in password managers.
Supported vault providers:
| Provider | URI Pattern | Requirements |
|---|---|---|
| 1Password | op://vault |
OP_SERVICE_ACCOUNT_TOKEN env var |
| Bitwarden | bw://org-id |
BW_ACCESS_TOKEN and BW_ORGANIZATION_ID env vars |
| File | file:///path |
None |
| Env | env://PREFIX_ |
None |
export OP_SERVICE_ACCOUNT_TOKEN="ops_..."
mcp-google --vault op://MyVault --credentials-name googleexport BW_ACCESS_TOKEN="..."
export BW_ORGANIZATION_ID="..."
mcp-google --vault bw://org-id --credentials-name googlemcp-google --vault file:///path/to/secrets --credentials-name googleThe CLI exposes one subcommand per MCP tool, plus serve and version.
mcp-google --help
mcp-google get-document-metadata <document-id-or-url> --credentials /path/to/service-account.json
mcp-google get-document-content <document-id-or-url> --include-metadata --include-images --include-tables -o pretty
mcp-google get-spreadsheet-metadata <spreadsheet-id-or-url> --credentials /path/to/service-account.json
mcp-google get-sheet-data <spreadsheet-id-or-url> --sheet-name "Sheet1" -o pretty
mcp-google get-presentation <presentation-id> --credentials /path/to/service-account.jsonUse mcp-google <command> --help for command-specific flags. See docs/cli.md for the full CLI reference.
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"google": {
"command": "/path/to/mcp-google",
"env": {
"GOOGLE_CREDENTIALS_FILE": "/path/to/service-account.json"
}
}
}
}{
"mcpServers": {
"google": {
"command": "/path/to/mcp-google",
"env": {
"GOAUTH_CREDENTIALS_FILE": "/path/to/credentials.json",
"GOAUTH_CREDENTIALS_ACCOUNT": "myaccount"
}
}
}
}{
"mcpServers": {
"google": {
"command": "/path/to/mcp-google",
"env": {
"OP_SERVICE_ACCOUNT_TOKEN": "ops_...",
"OMNITOKEN_VAULT_URI": "op://MyVault",
"OMNITOKEN_CREDENTIALS_NAME": "google"
}
}
}
}See docs/configuration/claude-desktop.md for more options including Bitwarden.
Get metadata about a document.
Input:
document_id(required) - The ID or URL of the Google Doc
Output:
title- Document titledocument_id- Document IDrevision_id- Current revision IDword_count- Approximate word countchar_count- Character countimage_count- Number of imagestable_count- Number of tablesheader_count- Number of headersfooter_count- Number of footers
Get the full structured content of a document.
Input:
document_id(required) - The ID or URL of the Google Docinclude_images(optional) - Include image information (default: false)include_tables(optional) - Include table content (default: false)include_headers(optional) - Include document headers (default: false)include_footers(optional) - Include document footers (default: false)
Output:
title- Document titlesections- Array of content sections:type- Section type ("heading", "paragraph")level- Heading level (1-6, for headings only)text- Section text contentstyle_id- Style identifier (e.g., "HEADING_1", "NORMAL_TEXT")
images- Array of images (if requested):object_id- Image element IDcontent_uri- Direct URL to imagesource_uri- Original source URLtitle- Image titledescription- Image description
tables- Array of tables (if requested):rows- Number of rowscolumns- Number of columnscells- 2D array of cell text content
headers- Array of header text (if requested)footers- Array of footer text (if requested)
Get all text from a document as a single plain text string.
Input:
document_id(required) - The ID or URL of the Google Doc
Output:
title- Document titletext- Full document text
Get text organized by paragraphs.
Input:
document_id(required) - The ID or URL of the Google Doc
Output:
title- Document titleparagraphs- Array of paragraph text strings
Get metadata about a spreadsheet.
Input:
spreadsheet_id(required) - The ID or URL of the Google Sheets spreadsheet
Output:
spreadsheet_id- Spreadsheet IDtitle- Spreadsheet titlelocale- Spreadsheet localetime_zone- Spreadsheet time zonesheet_count- Number of sheetsurl- Spreadsheet URL
List all sheets in a spreadsheet with their properties.
Input:
spreadsheet_id(required) - The ID or URL of the Google Sheets spreadsheet
Output:
spreadsheet_id- Spreadsheet IDtitle- Spreadsheet titlesheets- Array of sheet information:index- Sheet indexsheet_id- Sheet GIDtitle- Sheet titlesheet_type- Sheet type (GRID, etc.)hidden- Whether sheet is hiddenrow_count- Number of rowscolumn_count- Number of columnsfrozen_row_count- Number of frozen rows (if any)frozen_column_count- Number of frozen columns (if any)
Get cell values from a specific range.
Input:
spreadsheet_id(required) - The ID or URL of the Google Sheets spreadsheetrange(required) - A1 notation range (e.g., 'Sheet1!A1:D10', 'A:D', 'A1:D10')sheet_index(optional) - Zero-based sheet index (used when range doesn't include sheet name)sheet_name(optional) - Sheet name (mutually exclusive with sheet_index)value_format(optional) - Output format: 'formatted' (default), 'typed', 'raw'
Output:
spreadsheet_id- Spreadsheet IDrange- Resolved rangevalues- 2D array of cell values (format depends on value_format)
Get all data from a specific sheet.
Input:
spreadsheet_id(required) - The ID or URL of the Google Sheets spreadsheetsheet_index(optional) - Zero-based sheet index (default: 0)sheet_name(optional) - Sheet name (mutually exclusive with sheet_index and sheet_gid)sheet_gid(optional) - Sheet GID from URL (mutually exclusive with sheet_index and sheet_name)value_format(optional) - Output format: 'formatted' (default), 'typed', 'raw'include_metadata(optional) - Include sheet metadata (default: false)
Output:
spreadsheet_id- Spreadsheet IDsheet_name- Sheet namerange- Data rangevalues- 2D array of cell valuesmetadata- Sheet metadata (if requested)
Batch get values from multiple ranges in a single request.
Input:
spreadsheet_id(required) - The ID or URL of the Google Sheets spreadsheetranges(required) - Array of A1 notation rangesvalue_format(optional) - Output format: 'formatted' (default), 'typed', 'raw'
Output:
spreadsheet_id- Spreadsheet IDranges- Array of range results, each containing:range- Resolved rangevalues- 2D array of cell values
Get metadata about a presentation.
Input:
presentation_id(required) - The ID of the Google Slides presentation
Output:
title- Presentation titleslide_count- Number of slideslocale- Presentation localerevision_id- Current revision ID
List all slides in a presentation.
Input:
presentation_id(required) - The ID of the Google Slides presentation
Output:
slides- Array of slide information:object_id- Slide's unique identifierindex- Zero-based slide indextitle- Slide title (if present)element_count- Number of elements on the slide
Get the content of a specific slide.
Input:
presentation_id(required) - The ID of the Google Slides presentationslide_index(optional) - Zero-based slide indexslide_object_id(optional) - Slide's object ID
One of slide_index or slide_object_id must be provided.
Output:
text_content- Array of text strings from the slideelement_summary- Array of element details:object_id- Element's unique identifierelement_type- Type of element (shape, image, table, etc.)description- Element description or text preview
Get the speaker notes for a specific slide.
Input:
presentation_id(required) - The ID of the Google Slides presentationslide_index(optional) - Zero-based slide indexslide_object_id(optional) - Slide's object ID
One of slide_index or slide_object_id must be provided.
Output:
notes- Speaker notes text
Get all slide content in a single call - ideal for AI analysis of the entire presentation.
Input:
presentation_id(required) - The ID of the Google Slides presentationinclude_notes(optional) - Include speaker notes for each slide (default: false)
Output:
title- Presentation titleslides- Array of slide content:index- Zero-based slide indexobject_id- Slide's unique identifiertitle- Slide title (if present)text_content- Array of text strings from the slideimages- Array of images:object_id- Image element IDcontent_url- Direct URL to image (valid ~30 minutes)source_url- Original source URL (if available)alt_text- Image description
notes- Speaker notes (ifinclude_notesis true)
The document ID is in the URL when viewing a document:
https://docs.google.com/document/d/DOCUMENT_ID_HERE/edit
Note: Google Docs tools accept either the document ID or the full URL, including URLs with query strings and anchors:
https://docs.google.com/document/d/DOCUMENT_ID_HERE/edit?tab=t.0#heading=h.xyz
The spreadsheet ID is in the URL when viewing a spreadsheet:
https://docs.google.com/spreadsheets/d/SPREADSHEET_ID_HERE/edit
Note: Google Sheets tools accept either the spreadsheet ID or the full URL. URLs may include sheet GID and range:
https://docs.google.com/spreadsheets/d/SPREADSHEET_ID_HERE/edit#gid=123&range=A1:D10
The presentation ID is in the URL when viewing a presentation:
https://docs.google.com/presentation/d/PRESENTATION_ID_HERE/edit
MIT