Merge Unified's Google Docs integration Merge Agent Handler's Google Docs MCP server

Connect your AI Agents to Google Docs in minutes

Merge lets you securely connect your agents to Google Docs and thousands of tools instantly

Start building for free

Read docs

Google Docs

Learn more about Merge Agent Handler

Available tools

insert_image

Insert an inline image at a specific location

create_named_range

Create a named range (bookmark) in a document

delete_named_range

Delete a named range from a document

replace_named_range_content

Replace the content of a named range with new text. Named ranges auto-update their indices when surrounding content shifts, making them safer than replacetext for templated documents. Use createnamed_range first.

create_header

Create a header section at a section break in a document

delete_header

Delete a header section from a document

create_footer

Create a footer section at a section break in a document

delete_footer

Delete a footer section from a document

create_paragraph_bullets

Apply bullet or numbered list formatting to all paragraphs that overlap a range. Use bulletpreset to pick the list style. To remove bullets later, call deleteparagraph_bullets with the same range.

delete_paragraph_bullets

Remove bullet/numbered list formatting from all paragraphs that overlap a range. Paragraph text is preserved.

get_document_text

Read a Google Docs document as lightweight markdown-lite text (headings, bullets, tab titles). Use this for reading, summarizing, or searching content cheaply when you do NOT need to edit. Lossy: drops index ranges, styling, and images. Pass tabid (from listtabs) to read one tab. To edit or get exact structure, use get_document instead.

create_document

Create a new Google Docs document with optional title

get_document

Retrieve a Google Docs document's full structural JSON by ID: the index ranges needed to edit (insert/delete/replace by index), styling, and images. Use this to edit or when exact structure matters. Response can be large; pass fields (Google field mask) or tabid to shrink it. To only read or search text, use getdocumenttext. To list tabs, use listtabs.

get_document_end_index

Get the end index for appending content to a document

insert_image_in_table_cell

Insert an image into a table cell by table position

insert_text_in_table_cell

Insert text into a table cell by table position

create_and_populate_table

Create and populate a table with data in one operation

batch_update_document

Apply multiple updates to a document in a single operation

insert_text

Insert text at a specific location in a document

delete_text

Delete text from a specified range in a document

replace_text

Find and replace all occurrences of text in a document

format_text

Apply text formatting to a range in a document

format_paragraph

Apply paragraph formatting to a range in a document

append_text

Append text to the end of a document

create_footnote

Insert a footnote reference at the given index. The API creates a numbered reference and a corresponding footnote section at the page bottom; use insert_text with the returned footnoteId to populate footnote content.

find_text

Find literal text in a Google Docs document and return each match's UTF-16 start/end index and tabid, ready to pass to inserttext, deletetext, or formattext. Use this to locate where to edit instead of fetching the full JSON via getdocument. Case-insensitive by default. Searches tab bodies only (not headers/footers/footnotes). Pair with getdocument_text for reading.

insert_section_break

Insert a section break at a specific index. Use NEXTPAGE/EVENPAGE/ODD_PAGE to start a new page; CONTINUOUS to keep flow.

update_section_style

Update section style (columns, separator, content direction, margins) over a range. Provide at least one style field; use get_document to find section break indices.

update_document_style

Set page margins, page size, or background color on the document. Provide only the fields you want to change. Use 612pt x 792pt for US Letter, 595pt x 842pt for A4.

update_named_style

Redefine a named style document-wide (HEADING1 through HEADING6, NORMAL_TEXT, TITLE, SUBTITLE). All paragraphs using that named style will adopt the new typography. Use this for branded document templates instead of formatting paragraphs individually.

list_tabs

List all tabs in a Google Docs document, returning tab IDs, titles, and nesting only (no document content). Use this to discover tabids cheaply before reading or writing a specific tab; do not call getdocument just to enumerate tabs.

create_tab

Create a new tab in a Google Docs document

delete_tab

Delete a tab from a Google Docs document by tab ID. Use list_tabs to find tab IDs

update_tab_properties

Update a tab's properties (e.g. rename it) in a Google Docs document

insert_table

Insert a table with specified rows and columns

insert_table_row

Insert a new row into an existing table

insert_table_column

Insert a new column into an existing table

delete_table_row

Delete a row from an existing table

delete_table_column

Delete a column from an existing table

pin_table_header_rows

Pin the first N rows of a table as headers that repeat at the top of every page break. Pass 0 to unpin all header rows.

update_table_row_style

Set minimum row height and/or overflow prevention on one or more rows in a table. At least one of minrowheightpt or preventoverflow must be set. Omit row_indices to apply to every row.

update_table_column_properties

Set width on one or more columns in a table. Use widthtype=FIXEDWIDTH with widthpt for explicit widths, or EVENLYDISTRIBUTED to mark the targeted columns as evenly distributed (Google computes their widths as the remaining table width shared across all EVENLYDISTRIBUTED columns in the table). Empty columnindices targets every column.

update_table_cell_style

Update visual styling on a single table cell - background color, borders, padding, vertical alignment. Cell is identified by its containing table's start index plus zero-based row/column. Use inserttable or createandpopulatetable first.

merge_table_cells

Merge a rectangular block of table cells into one. Specify the upper-left and lower-right cell positions. Common in header rows and summary tables. Use get_document to find the table's start index.

unmerge_table_cells

Reverse a previous mergetablecells operation, restoring the cells in the specified range to individual cells. Use get_document to find the table's start index and the bounds of a previously merged region.

validate_credential

Validate Google Docs credentials. Verifies credentials during setup.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}

Copy Code

FAQs on using Merge's Google Docs MCP server

What is a Google Docs MCP?

It's an MCP server that connects your agents to Google Docs via tools. Your agents can invoke these tools to create documents, insert and format text, manage tables, add headers and footers, and more.

Google doesn't offer a standalone MCP server purpose built for Google Docs, but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the Google Docs MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

Automated report generation: When a data pipeline finishes processing, an agent calls <code class="blog_inline-code">create_document</code> and uses <code class="blog_inline-code">append_text</code> and <code class="blog_inline-code">create_and_populate_table</code> to generate a formatted report with section headers and data tables, ready to share without anyone touching a doc manually

Contract population from CRM data: When a deal closes in Salesforce, an agent calls <code class="blog_inline-code">replace_text</code> to fill in placeholders in a template document with the customer name, contract terms, and start date, producing a draft ready for review in seconds

Meeting notes structuring: After a call transcript is available, an agent calls <code class="blog_inline-code">insert_text</code> and <code class="blog_inline-code">format_paragraph</code> to organize raw content into a clean Google Doc with section headings, a summary, and a clearly formatted action item list

Running project log updates: When a Jira ticket is resolved, an agent calls <code class="blog_inline-code">append_text</code> to add a formatted entry to a shared project log document, keeping a persistent record without requiring anyone to manually update the doc after each change

What are popular tools for Google Docs' MCP server?

Here are some of the most commonly used tools:

<code class="blog_inline-code">create_document</code> creates a new Google Doc with a specified title. Use this when an agent needs to generate a fresh document in response to a trigger, like a new project kickoff or a completed data run

<code class="blog_inline-code">append_text</code> adds text to the end of an existing document. Good for agents that maintain a running log or need to accumulate entries over time without overwriting previous content

<code class="blog_inline-code">insert_text</code> places text at a specific position in the document body. Call this when an agent needs to inject content at a precise location rather than at the end of the document

<code class="blog_inline-code">replace_text</code> finds all instances of a string in the document and swaps them with a new value. Useful for agents that fill in template documents with data pulled from an external system at generation time

<code class="blog_inline-code">format_text</code> applies character-level formatting such as bold, italic, font size, or color to a specified text range. Helpful when an agent needs to produce a consistently styled document rather than plain unformatted output

<code class="blog_inline-code">create_and_populate_table</code> inserts a new table into the document and fills it with provided row and column data in one call. Use this when an agent needs to embed structured data, like a summary table or comparison grid, directly in a document

What makes Merge Agent Handler's Google Docs MCP server better than alternative Google Docs MCP servers?

A few things distinguish Merge Agent Handler's Google Docs MCP server from building your own or relying on a standalone option:

Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Google Docs, this means you can prevent document body content, named ranges, and personally identifiable text from being read or written by an agent even when it has broad access to your Drive

Managed authentication and credentials: Merge stores and refreshes Google Docs OAuth credentials on your behalf. You never expose tokens to an agent or manage the complexity of Google's token refresh cycles manually

Real-time observability and audit trail: Every tool call made against Google Docs is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what text an agent inserted, replaced, or formatted without adding any instrumentation to your own stack

Tool Packs and controlled access: Tool Packs let you bundle specific Google Docs tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Google Docs MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account and navigate to Tool Packs (collections of connector tools scoped to a specific use case).

2. Create a new Tool Pack, then find and enable the Google Docs connector. Choose which tools to include: enable read tools like <code class="blog_inline-code">get_document</code> for retrieval use cases, or add write tools like <code class="blog_inline-code">create_document</code> and <code class="blog_inline-code">append_text</code> if your agent needs to generate or modify documents.

3. Add a Registered User inside the Tool Pack. This is the identity context under which your agent operates. Merge generates a unique MCP URL scoped to this user once it's created.

4. From the Registered User detail page, authenticate Google Docs by completing the OAuth flow. Merge stores and manages the credentials going forward.

5. Copy the MCP URL from the Tool Pack detail page and generate an API key from Settings. You'll need both to connect your agent.

6. Add the MCP server to your agent or IDE using the MCP URL and API key. Your Google Docs tools are now accessible through that endpoint.