Can it produce properly formatted documents, not just plain text?

Yes — formatting is most of the toolset. update_paragraph_style applies headings and nested lists, insert_doc_elements adds tables and page breaks, create_table_with_data builds populated tables in one call, and modify_doc_text handles inline formatting and links.

How do I get a Google Doc into Markdown for a repo or wiki?

get_doc_as_markdown exports the document with formatting preserved. The reverse direction works too: the Drive service’s import_to_google_doc turns Markdown into an editable Doc.

Can an assistant work with comments and suggestions?

list_document_comments reads every comment thread, and manage_document_comment can create, reply to, or resolve them — useful for agents doing a review pass on a shared draft.

What stops an edit from landing in the wrong place?

inspect_doc_structure exposes the document’s element tree so the assistant can locate the exact paragraph, table cell, or index before editing, and debug_table_structure does the same for complex tables.

Google Docs MCP Server

Create, edit, style, and export Google Docs with the deepest toolset in the server.

Quick start Jump to all 19 tools →

Docs is the deepest service in Workspace MCP — nineteen tools, because document editing has real structure. Beyond create_doc and modify_doc_text, there are dedicated tools for paragraph styling, nested lists, tables built from data, headers and footers, inline images, and document tabs.

Two tools matter especially for developer workflows: get_doc_as_markdown exports a formatted document straight to Markdown for your repo, and inspect_doc_structure lets an assistant understand a document’s element tree before attempting a precise edit.

What you can ask

“Draft a project brief from these notes with proper heading structure and a summary table”
“Export the onboarding doc to Markdown so I can commit it to the wiki”
“Find every mention of the old product name across the doc and replace it”

All 19 Google Docs MCP tools

Expand any tool for its full parameter list. Tiers control how many tools the server registers: start lean with --tool-tier core and step up to extended or complete when a workflow needs more.

get_doc_content Core Extract plain text document content. 2

Parameter	Description
`document_id` required	ID of the document to retrieve.
`tab_id`	Read a single tab instead of the main document body. Take the ID from `inspect_doc_structure`.

create_doc Core Create new documents. 2

Parameter	Description
`title` required	The title for the new document.
`content`	Initial text content for the document.

modify_doc_text Core Modify document text with formatting and links. 12

Parameter	Description
`document_id` required	ID of the document to update.
`start_index` required	Start position for operation (0-based).
`end_index`	End position for text replacement/formatting (if not provided with text, text is inserted).
`text`	New text to insert or replace with (optional - can format existing text without changing it).
`bold`	Whether to make text bold (True/False/None to leave unchanged).
`italic`	Whether to make text italic (True/False/None to leave unchanged).
`underline`	Whether to underline text (True/False/None to leave unchanged).
`font_size`	Font size in points.
`font_family`	Font family name (e.g., "Arial", "Times New Roman").
`text_color`	Foreground text color (#RRGGBB).
`background_color`	Background/highlight color (#RRGGBB).
`link_url`	Hyperlink URL (http/https).

search_docs Extended Search docs by name. 2

Parameter	Description
`query` required	Search query to find documents by name.
`page_size`	Maximum number of results to return.

find_and_replace_doc Extended Find and replace text. 4

Parameter	Description
`document_id` required	ID of the document to update.
`find_text` required	Text to search for.
`replace_text` required	Text to replace with.
`match_case`	Whether to match case exactly.

list_docs_in_folder Extended List docs in a Drive folder. 2

Parameter	Description
`folder_id`	The ID of the folder. Defaults to root.
`page_size`	Maximum number of documents to return.

insert_doc_elements Extended Insert tables, lists, and page breaks. 7

Parameter	Description
`document_id` required	ID of the document to update.
`element_type` required	Type of element to insert ("table", "list", "page_break").
`index` required	Position to insert element (0-based).
`rows`	Number of rows for table (required for table).
`columns`	Number of columns for table (required for table).
`list_type`	Type of list ("UNORDERED", "ORDERED") (required for list).
`text`	Initial text content for list items.

update_paragraph_style Extended Apply heading and paragraph styles, including nested lists and per-edge borders. 13

Parameter	Description
`document_id` required	Document ID to modify.
`start_index` required	Start position (1-based).
`end_index` required	End position (exclusive) - should cover the entire paragraph.
`heading_level`	Heading level 0-6 (0 = NORMAL_TEXT, 1 = H1, 2 = H2, etc.).
`alignment`	Text alignment.
`line_spacing`	Line spacing value.
`border_edges`	Border edges to update ('top', 'bottom', 'left', 'right', 'between'). Omit to update all four outer edges.
`border_color`	Border color as #RRGGBB. Defaults to black.
`border_width`	Border width in points. Defaults to 1.
`border_padding`	Border padding in points. Defaults to 4.
`border_dash`	Border dash style ('SOLID', 'DOT', or 'DASH'). Defaults to 'SOLID'.
`list_type`	List type for creating lists.
`list_nesting_level`	Nesting level for lists.

get_doc_as_markdown Extended Export a document as formatted Markdown. 5

Parameter	Description
`document_id` required	ID of the Google Doc (or full URL).
`include_comments`	Whether to include comments (default: True).
`comment_mode`	How to display comments.
`include_resolved`	Whether to include resolved comments (default: False).
`tab_id`	Export a single tab instead of the main document body. Take the ID from `inspect_doc_structure`.

export_doc_to_pdf Extended Export a doc to PDF. 3

Parameter	Description
`document_id` required	ID of the Google Doc to export.
`pdf_filename`	Name for the PDF file (optional - if not provided, uses original name + "_PDF").
`folder_id`	Drive folder ID to save PDF in (optional - if not provided, saves in root).

list_document_comments Extended List all document comments. —

manage_document_comment Extended Create, reply, or resolve comments. —

insert_doc_image Complete Insert images from Drive or URLs. 5

Parameter	Description
`document_id` required	ID of the document to update.
`image_source` required	Drive file ID or public image URL.
`index` required	Position to insert image (0-based).
`width`	Image width in points (optional).
`height`	Image height in points (optional).

update_doc_headers_footers Complete Update headers and footers. 4

Parameter	Description
`document_id` required	ID of the document to update.
`section_type` required	Type of section to update ("header" or "footer").
`content` required	Text content for the header/footer.
`header_footer_type`	Type of header/footer ("DEFAULT", "FIRST_PAGE_ONLY", "EVEN_PAGE").

batch_update_doc Complete Execute multiple doc operations in one call. 2

Parameter	Description
`document_id` required	ID of the document to update.
`operations` required	List of operation dictionaries.

inspect_doc_structure Complete Inspect structural document elements. Both modes also report paragraph layout stats: empty-paragraph counts, up to 100 paragraph ranges with a truncation flag, and whether the last paragraph is empty or a list item. 4

Parameter	Description
`document_id` required	ID of the document to inspect.
`detailed`	Whether to return detailed structure information. Detailed output adds list membership and object anchors.
`tab_id`	Inspect a single tab instead of the main document body.
`preview_chars`	Maximum characters of paragraph, header, and footer text preview (default 100). Pass `0` or `None` for the full text, which you need to locate a token inside a longer paragraph: add its UTF-16 offset to the paragraph's `start_index`.

create_table_with_data Complete Create populated tables. 4

Parameter	Description
`document_id` required	ID of the document to update.
`table_data` required	2D list of strings - EXACT format: [["col1", "col2"], ["row1col1", "row1col2"]].
`index` required	Document position (get from inspect_doc_structure 'total_length').
`bold_headers`	Whether to make first row bold (default: true).

debug_table_structure Complete Debug table structures. 2

Parameter	Description
`document_id` required	ID of the document to inspect.
`table_index`	Which table to debug (0 = first table, 1 = second table, etc.).

manage_doc_tab Complete Create, rename, delete, or populate document tabs from markdown. 8

Parameter	Description
`document_id` required	ID of the document to update.
`action` required	'create', 'rename', 'delete', or 'populate_from_markdown'.
`tab_id`	Tab ID (required for rename, delete, and populate).
`title`	Tab title (required for create and rename).
`index`	Position for the new tab.
`parent_tab_id`	Parent tab ID for nested tabs.
`markdown_text`	Markdown content for populate_from_markdown.
`replace_existing`	Whether populate replaces existing tab content (default: True).

Every service in one reference: full API documentation →

OAuth scopes

The server requests only the scopes for the services you enable. In read-only mode it requests just the readonly variants and skips registering write tools entirely.

documents.readonly read document content and structure
documents create and edit documents
drive.readonly search and list docs in folders

Google Docs MCP questions

Can it produce properly formatted documents, not just plain text?: Yes — formatting is most of the toolset. update_paragraph_style applies headings and nested lists, insert_doc_elements adds tables and page breaks, create_table_with_data builds populated tables in one call, and modify_doc_text handles inline formatting and links.
How do I get a Google Doc into Markdown for a repo or wiki?: get_doc_as_markdown exports the document with formatting preserved. The reverse direction works too: the Drive service’s import_to_google_doc turns Markdown into an editable Doc.
Can an assistant work with comments and suggestions?: list_document_comments reads every comment thread, and manage_document_comment can create, reply to, or resolve them — useful for agents doing a review pass on a shared draft.
What stops an edit from landing in the wrong place?: inspect_doc_structure exposes the document’s element tree so the assistant can locate the exact paragraph, table cell, or index before editing, and debug_table_structure does the same for complex tables.

Works alongside

All services: Gmail MCP Google Drive MCP Google Calendar MCP Google Docs MCP Google Sheets MCP Google Slides MCP Google Forms MCP Google Tasks MCP Google Contacts MCP Google Chat MCP Google Custom Search MCP Google Apps Script MCP