Google Docs - Prisme.ai

The Google Docs app provides read/write access to a user’s Google Docs documents through the Docs API v1. It can be used either as a Builder app (automations call Docs instructions directly) or as a remote MCP server consumed by an AI agent. Each tenant configures its own Google OAuth Application; end-users sign in with their own Google account and tokens are stored per (user × tenant). The connector exposes 2 base Docs operations plus ~30 atomic editing operations — each wraps a single batchUpdate request — grouped into 9 entity tools covering documents, text, paragraphs, tables, document style, headers/footers, media, named ranges and raw batch.

Documents & Text

Create, retrieve, insert, delete, replace and style text across a Google Doc

Structure & Tables

Manage paragraphs, bullets, tables, columns/rows, headers, footers, footnotes and document style

Media & Named Ranges

Insert and replace inline images, manage positioned objects, page breaks and named ranges

Prerequisites

A Google account with access to the documents you want to expose. For Google Workspace, the workspace admin may need to allow third-party OAuth apps.
A Google Cloud project with the Google Docs API enabled at console.cloud.google.com/apis/library/docs.googleapis.com. Enable the Drive API too if you plan to locate documents via the Google Drive connector.
A Google OAuth 2.0 Client of type Web application, created at console.cloud.google.com/apis/credentials. The Authorized redirect URIs must contain the value shown in the OAuth Callback URL field of the installed app instance (auto-populated on install — copy it back into the Google Cloud Console after installation).
An OAuth consent screen configured in the Google Cloud project. While the app is in Testing state, add the end-user’s email to Test users. The default scopes documents + drive.file go through Google’s verification process when the consent screen moves to Production.
Base URL (default: https://docs.googleapis.com/v1)

The Google Docs API cannot list or search documents. To find documents or obtain a documentId, use the Google Drive connector — filter mimeType = application/vnd.google-apps.document — then call documents.get here.

Usage as App
Usage as MCP

Installation

Go to Apps in your workspace
Search for Google Docs and install it
Open the app instance configuration and fill in the required fields

Configuration

Field	Description
Google Docs API Base URL	Base URL of the Docs API (default `https://docs.googleapis.com/v1`)
Google OAuth Access Token (fallback)	Optional static OAuth access token used as a shared fallback for all users of this tenant. Stored as a workspace secret. Most deployments leave this empty and rely on per-user OAuth instead.
Google OAuth2 Client ID	Google OAuth Application Client ID. Create an OAuth client of type Web application in the Google Cloud Console
Google OAuth2 Client Secret	Google OAuth Client Secret, stored as a workspace secret
OAuth Callback URL	Auto-populated on install — paste this value into the Authorized redirect URIs list of your Google OAuth client
OAuth Authorize URL	Default `https://accounts.google.com/o/oauth2/v2/auth`
OAuth Token URL	Default `https://oauth2.googleapis.com/token`
OAuth Revoke URL	Default `https://oauth2.googleapis.com/revoke`
OAuth Scopes	Space-separated Google API scopes. Default `https://www.googleapis.com/auth/documents https://www.googleapis.com/auth/drive.file`
Access Token TTL (seconds)	Default 3600 (Google access tokens expire in 1h; refresh is automatic)
MCP Endpoint	Auto-populated on install — URL of the MCP endpoint for this instance
MCP API Key	Auto-populated on install — signed key used in the `mcp-api-key` header. Do not modify

MCP Endpoint, MCP API Key and OAuth Callback URL are generated automatically by the onInstall flow. The OAuth credentials (Google OAuth2 Client ID, Google OAuth2 Client Secret) must be filled in manually after creating the OAuth client in the Google Cloud Console.

Authorize end-users

Once the app instance is configured, each end-user authorizes their own Google account through a browser-based consent screen:

Trigger the connect flow

From an MCP client (Agent Creator capability or any tool client), call any data tool. If no OAuth session exists for the current user × tenant, the MCP server returns a connector_auth_required payload with a connect_url. Alternatively, call the connect tool explicitly to receive the same payload.

Open the connect URL

Open the returned URL in a browser tab where the user is already authenticated to Prisme.ai. The platform redirects to the Google OAuth consent screen.

Grant access

The user reviews the requested scopes (default documents + drive.file) and clicks Allow. Google redirects back to the platform’s oauthCallback webhook.

Confirmation

The user sees a Connection complete page and can close the tab. The platform has stored an access token plus refresh token as user-scoped secrets — both are tenant-prefixed so they do not leak across app instances.

Each user’s OAuth tokens are scoped per (user × tenant). A user who has authorized in tenant A does not gain access in tenant B — they must run the connect flow again per app instance. Access tokens are refreshed automatically from the stored refresh token.

Available Instructions

Every instruction resolves credentials from the workspace configuration. All editing operations target a single documentId (obtained either from createDocument or via the Google Drive connector). Editing instructions internally wrap a single batchUpdate request; use batchUpdate directly to compose multiple changes in one atomic call.

Documents

Instruction	Arguments
`createDocument`	`title`*
`getDocument`	`documentId`*, `suggestionsViewMode`, `includeTabsContent`

Text

Instruction	Arguments
`insertText`	`documentId`, `text`, `location`, `endOfSegmentLocation`
`deleteContentRange`	`documentId`, `range`
`replaceAllText`	`documentId`, `containsText`, `replaceText`*, `tabsCriteria`
`updateTextStyle`	`documentId`, `textStyle`, `fields`, `range`

Paragraphs

Instruction	Arguments
`createParagraphBullets`	`documentId`, `range`, `bulletPreset`*
`deleteParagraphBullets`	`documentId`, `range`
`updateParagraphStyle`	`documentId`, `paragraphStyle`, `fields`, `range`

Tables

Instruction	Arguments
`insertTable`	`documentId`, `rows`, `columns`*, `location`, `endOfSegmentLocation`
`insertTableRow`	`documentId`, `tableCellLocation`, `insertBelow`
`insertTableColumn`	`documentId`, `tableCellLocation`, `insertRight`
`deleteTableRow`	`documentId`, `tableCellLocation`
`deleteTableColumn`	`documentId`, `tableCellLocation`
`mergeTableCells`	`documentId`, `tableRange`
`unmergeTableCells`	`documentId`, `tableRange`
`pinTableHeaderRows`	`documentId`, `tableStartLocation`, `pinnedHeaderRowsCount`*
`updateTableCellStyle`	`documentId`, `tableCellStyle`, `fields`*, `tableRange`, `tableStartLocation`
`updateTableColumnProperties`	`documentId`, `tableStartLocation`, `columnIndices`, `tableColumnProperties`, `fields`*
`updateTableRowStyle`	`documentId`, `tableStartLocation`, `rowIndices`, `tableRowStyle`, `fields`*

Document Style

Instruction	Arguments
`updateDocumentStyle`	`documentId`, `documentStyle`, `fields`*
`updateSectionStyle`	`documentId`, `range`, `sectionStyle`, `fields`

Headers, Footers & Footnotes

Instruction	Arguments
`createHeader`	`documentId`, `type`, `sectionBreakLocation`
`createFooter`	`documentId`, `type`, `sectionBreakLocation`
`createFootnote`	`documentId`*, `location`, `endOfSegmentLocation`
`deleteHeader`	`documentId`, `headerId`
`deleteFooter`	`documentId`, `footerId`

Media

Instruction	Arguments
`insertInlineImage`	`documentId`, `uri`, `objectSize`, `location`, `endOfSegmentLocation`
`replaceImage`	`documentId`, `imageObjectId`, `uri`*, `imageReplaceMethod`
`insertPageBreak`	`documentId`*, `location`, `endOfSegmentLocation`
`deletePositionedObject`	`documentId`, `objectId`
`updateEmbeddedObjectPosition`	`documentId`, `objectId`, `newPosition`, `fields`

Named Ranges

Instruction	Arguments
`createNamedRange`	`documentId`, `name`, `range`*
`deleteNamedRange`	`documentId`*, `namedRangeId`, `name`, `tabsCriteria`
`replaceNamedRangeContent`	`documentId`, `text`, `namedRangeId`, `namedRangeName`, `tabsCriteria`

Batch

Instruction	Arguments
`batchUpdate`	`documentId`, `requests`, `writeControl`

Arguments flagged with * are required.

DSUL Examples

Create a Doc and populate it with a title + intro

- Google Docs.documents:
    action: create
    title: '{{report.name}} — {{run.date}}'
    output: created
- Google Docs.text:
    action: insert
    documentId: '{{created.documentId}}'
    text: 'Executive summary'
    location:
      index: 1
- Google Docs.paragraphs:
    action: updateStyle
    documentId: '{{created.documentId}}'
    paragraphStyle:
      namedStyleType: HEADING_1
    fields: namedStyleType
    range:
      startIndex: 1
      endIndex: 18

Replace placeholders across an existing template

- Google Docs.text:
    action: replaceAll
    documentId: '{{templateDocId}}'
    containsText:
      text: '{{{{customer_name}}}}'
      matchCase: false
    replaceText: '{{customer.name}}'
- Google Docs.text:
    action: replaceAll
    documentId: '{{templateDocId}}'
    containsText:
      text: '{{{{order_total}}}}'
    replaceText: '{{order.total}} €'

Insert a 3×4 table and merge the header row

- Google Docs.tables:
    action: insert
    documentId: '{{docId}}'
    rows: 4
    columns: 3
    endOfSegmentLocation: {}
- Google Docs.tables:
    action: merge
    documentId: '{{docId}}'
    tableRange:
      tableCellLocation:
        tableStartLocation:
          index: 200
        rowIndex: 0
        columnIndex: 0
      rowSpan: 1
      columnSpan: 3

Build a multi-step report atomically with `batchUpdate`

- Google Docs.batch:
    action: update
    documentId: '{{docId}}'
    requests:
      - insertText:
          text: 'Q2 Results\n'
          location:
            index: 1
      - updateParagraphStyle:
          paragraphStyle:
            namedStyleType: HEADING_1
          fields: namedStyleType
          range:
            startIndex: 1
            endIndex: 11
      - insertPageBreak:
          endOfSegmentLocation: {}

The Google Docs app ships with a built-in MCP server. Each app instance gets its own signed mcp-api-key that encodes the workspace ID and a credentials lookup URL — the Google Docs API token itself is never passed through headers and is resolved server-side from the app configuration plus the per-user OAuth session.

Plug into an Agent Creator capability

Agents consume MCP servers directly through Agent Creator capabilities. This is the preferred way to expose Google Docs to an agent.

Create or open a workspace

From the Prisme.ai console, create a new workspace (or open the one that will host the connector).

Install the Google Docs app

Open the workspace Imports panel, search for Google Docs and install it.

Configure the credentials

Open the freshly installed app instance settings and fill in the OAuth Client ID and Client Secret (see the Usage as App tab for the field-by-field reference).

Copy the MCP endpoint and API key

Still on the app instance configuration page, copy the values of MCP Endpoint and MCP API Key — both are generated automatically on install.

Open Agent Creator

Switch to Agent Creator and open the agent you want to extend.

Add a capability

Add a new capability to the agent:

If a dedicated Google Docs capability exists — select it and paste the MCP API Key into the mcp-api-key field. The server URL is already wired.
Otherwise — select the generic custom_mcp capability, paste the MCP Endpoint into the Server URL field, then open the Headers field and add an mcp-api-key entry whose value is the MCP API Key copied earlier:
```
{
  "mcp-api-key": "your-mcp-api-key"
}
```

Save

The agent now has access to every Google Docs tool exposed by the MCP server.

Brief the agent in its system prompt

Wiring the capability is not enough — the agent also needs to know the MCP exists and when to reach for it. Add a short paragraph to the agent’s system prompt. Copy-pasteable starter:

You have access to the Google Docs MCP server. Use it whenever the user asks you to write, edit or read a Google Doc — creating documents, inserting or replacing text, building tables, applying styles, adding headers/footers, or stamping templated reports. The first call may return a connect_url asking the user to authorize their Google account; relay it as-is. The Docs API cannot list documents — if the user references "their docs" without an ID, pair this with the Google Drive MCP. Always confirm with the user before any destructive change (delete content, replaceAll on a live doc, delete header/footer).

Refine the trigger keywords (resource names, business domains, typical user phrasings) so the agent reliably picks up the right intent in your context.

Legacy MCP Install (Advanced > Tools)

Use this flow to plug the Google Docs MCP into an AI Knowledge agent that does not yet support the native MCP picker.

Install the Google Docs app

Install and configure the app in the same workspace as your agent (see the Usage as App tab). Once configured, mcpEndpoint and mcpApiKey are auto-populated.

Copy the MCP credentials

Open the app instance config and copy the values of MCP Endpoint and MCP API Key.

Open your AI Knowledge project

Navigate to Advanced > Tools.

Add an MCP tool

Click Add and select the MCP tab.

Fill in the endpoint

Paste the MCP Endpoint URL copied from the app instance.

Add the auth header

In the Headers field, add the signed API key:

{
  "mcp-api-key": "your-mcp-api-key"
}

Save

The agent can now list and call Google Docs tools through the MCP endpoint.

The signed mcp-api-key encodes the workspace ID and the getConfig webhook URL. The MCP server validates the signature using the central app secret and transparently fetches the OAuth client credentials and base URL from the installed app, then resolves the calling user’s stored Google access token. Credentials are cached per tenant for 10 minutes; user OAuth tokens are refreshed on demand.

Output Formats

Every tool accepts an outputFormat parameter that controls the MCP response shape:

verbose (default) — human-readable text for LLM consumption
structured — machine-readable JSON in structuredContent
both — both text and structured content

Available Tools

The MCP server exposes 9 entity-level tools (each with an action argument to select the operation) plus the 2 generic OAuth tools.

`documents`

Action	Description
`create`	Create a blank Google Doc with a given title
`get`	Retrieve a Doc (body, styles, named ranges, tabs content)

`text`

Action	Description
`insert`	Insert text at a location or at end of segment
`delete`	Delete content between two indexes
`replaceAll`	Replace every match of a string with a new value across the document
`updateStyle`	Update text style on a range (bold, italic, fontSize, color, link, …)

`paragraphs`

Action	Description
`createBullets`	Add bullets to one or more paragraphs
`deleteBullets`	Remove bullets from paragraphs
`updateStyle`	Update paragraph-level style (alignment, headingId, indent, spacing)

`tables`

Action	Description
`insert`	Insert a table with given rows and columns
`insertRow`	Insert a row above/below a table cell
`insertColumn`	Insert a column left/right of a table cell
`deleteRow`	Delete a table row
`deleteColumn`	Delete a table column
`merge`	Merge a rectangular range of table cells
`unmerge`	Unmerge previously merged table cells
`pinHeaderRows`	Configure how many header rows are pinned
`updateCellStyle`	Update style of one or more cells (background, borders, padding)
`updateColumnProperties`	Update table column properties (e.g. width)
`updateRowStyle`	Update style of one or more rows (min height, header rows)

`documentStyle`

Action	Description
`update`	Update document-level style (page size, margins, page numbers)
`updateSection`	Update style of a section (columns, page size override)

`headersFooters`

Action	Description
`createHeader`	Create a new header (default or first-page-header)
`createFooter`	Create a new footer (default or first-page-footer)
`createFootnote`	Create a footnote at a location
`deleteHeader`	Delete a header by ID
`deleteFooter`	Delete a footer by ID

`media`

Action	Description
`insertImage`	Insert an inline image at a location from a public URL
`replaceImage`	Replace the source of an existing image by its `objectId`
`insertPageBreak`	Insert a page break at a location
`deletePositioned`	Delete a positioned object (floating image, drawing)
`updatePosition`	Move or resize a positioned object

`namedRanges`

Action	Description
`create`	Create a named range over an existing text range
`delete`	Delete a named range by ID or by name
`replaceContent`	Replace the textual content within a named range

`batch`

Action	Description
`update`	Apply multiple Doc updates in one atomic `batchUpdate` request

OAuth Session

Tool	Description
`connect`	Initiate an OAuth connection to Google Docs. Returns a `connect_url` for the user to click. Prefer calling data tools directly — they auto-handle authentication.
`disconnect`	Disconnect the current Google Docs OAuth session and revoke the access token (RFC 7009)

Tool Details

`documents` (action: `create`)

{
  "name": "documents",
  "arguments": {
    "action": "create",
    "title": "Q2 financial report"
  }
}

Parameter	Required	Description
`action`	✓	Must be `create`
`title`	✓	Document title (max 255 chars)

The response includes the newly-created documentId, which is then used by every editing tool.

`text` (action: `insert`)

{
  "name": "text",
  "arguments": {
    "action": "insert",
    "documentId": "1abcdEF...",
    "text": "Executive summary\n",
    "location": { "index": 1 }
  }
}

Parameter	Required	Description
`action`	✓	Must be `insert`
`documentId`	✓	Target document
`text`	✓	The text to insert
`location`	–	`{ index }` — character offset where the text is inserted
`endOfSegmentLocation`	–	Use to append to the end of the body, a header, footer or footnote

Indexes in Google Docs are 1-based and refer to UTF-16 code units inside a segment. Inserting changes downstream indexes — when chaining multiple inserts, prefer batchUpdate with explicit indexes computed up-front, or insert in reverse order.

`text` (action: `replaceAll`)

{
  "name": "text",
  "arguments": {
    "action": "replaceAll",
    "documentId": "1abcdEF...",
    "containsText": {
      "text": "{{customer_name}}",
      "matchCase": false
    },
    "replaceText": "Acme Corp"
  }
}

Parameter	Required	Description
`action`	✓	Must be `replaceAll`
`documentId`	✓	Target document
`containsText`	✓	`{ text, matchCase }` — the substring to match
`replaceText`	✓	The replacement value
`tabsCriteria`	–	Restrict the replacement to specific tab IDs

`tables` (action: `insert`)

{
  "name": "tables",
  "arguments": {
    "action": "insert",
    "documentId": "1abcdEF...",
    "rows": 4,
    "columns": 3,
    "endOfSegmentLocation": {}
  }
}

Parameter	Required	Description
`action`	✓	Must be `insert`
`documentId`	✓	Target document
`rows`	✓	Number of rows (≥1)
`columns`	✓	Number of columns (≥1)
`location`	–	Insert at a specific index
`endOfSegmentLocation`	–	Insert at the end of the body / header / footer

`media` (action: `insertImage`)

{
  "name": "media",
  "arguments": {
    "action": "insertImage",
    "documentId": "1abcdEF...",
    "uri": "https://example.com/charts/q2.png",
    "objectSize": {
      "width":  { "magnitude": 400, "unit": "PT" },
      "height": { "magnitude": 240, "unit": "PT" }
    },
    "endOfSegmentLocation": {}
  }
}

Parameter	Required	Description
`action`	✓	Must be `insertImage`
`documentId`	✓	Target document
`uri`	✓	Publicly accessible image URL (Google fetches and re-hosts the image)
`objectSize`	–	`{ width, height }` with `magnitude` + `unit: PT`
`location`	–	Insert at a specific index
`endOfSegmentLocation`	–	Insert at the end of a segment

`batch` (action: `update`)

{
  "name": "batch",
  "arguments": {
    "action": "update",
    "documentId": "1abcdEF...",
    "requests": [
      { "insertText": { "text": "Q2 results\n", "location": { "index": 1 } } },
      { "updateParagraphStyle": {
          "paragraphStyle": { "namedStyleType": "HEADING_1" },
          "fields": "namedStyleType",
          "range": { "startIndex": 1, "endIndex": 11 }
        }
      },
      { "insertPageBreak": { "endOfSegmentLocation": {} } }
    ]
  }
}

Parameter	Required	Description
`action`	✓	Must be `update`
`documentId`	✓	Target document
`requests`	✓	Ordered list of Docs `Request` objects applied atomically
`writeControl`	–	`{ requiredRevisionId, targetRevisionId }` for optimistic concurrency

Error Handling

HTTP Status	Meaning	Typical Cause
`400`	Bad Request	Malformed request, invalid `Range`/`Location`, conflicting `requests` in a batch
`401`	Unauthorized	Missing / expired OAuth token, revoked refresh token, user has not connected yet
`403`	Forbidden	Docs API disabled in the Google Cloud project, scope insufficient, user lost access to the document
`404`	Not Found	Document does not exist or the user has no access (most often the latter)
`409`	Conflict	Optimistic concurrency failure via `writeControl.requiredRevisionId`
`429`	Rate Limited	Per-user or per-project quota exhausted. Back off and retry
`500` / `503`	Server Error	Transient Google Docs API error. Retry with exponential backoff

Common Issues

“Not configured” — The app instance has no OAuth Client ID/Secret. Create an OAuth client in the Google Cloud Console and paste the credentials into the app configuration. “Invalid API key” (MCP) — The mcp-api-key header does not match the central app secret. Reinstall the app instance to regenerate a signed key. “Credentials lookup failed” — The MCP endpoint could not reach the getConfig webhook of the installed app. Verify that the app instance is still installed in the expected workspace. connector_auth_required — The calling user has no Google OAuth session yet for this tenant. The response payload includes a connect_url; relay it to the user so they can authorize their Google account. redirect_uri_mismatch during the OAuth dance — The value of OAuth Callback URL in the app config has not been added to the Authorized redirect URIs of the Google OAuth client. Copy it back into the Google Cloud Console and retry. The user does not have sufficient permissions for file … (403) — The default scope drive.file only grants access to files the user created with the app or opened with the app. To work with arbitrary user documents, broaden the scope to https://www.googleapis.com/auth/documents.readonly + drive.readonly (read-only) or documents + drive (full Drive). Broader scopes require Google verification before going to production. “No documentId” / cannot list documents — The Google Docs API does not expose a list/search endpoint. Pair this connector with the Google Drive connector to enumerate documents (mimeType = application/vnd.google-apps.document), then call documents.get with the returned IDs.

Documentation Index

Documents & Text

Structure & Tables

Media & Named Ranges

​Prerequisites

​Installation

​Configuration

​Authorize end-users

​Available Instructions

​Documents

​Text

​Paragraphs

​Tables

​Document Style

​Headers, Footers & Footnotes

​Media

​Named Ranges

​Batch

​DSUL Examples

​Create a Doc and populate it with a title + intro

​Replace placeholders across an existing template

​Insert a 3×4 table and merge the header row

​Build a multi-step report atomically with batchUpdate

​Plug into an Agent Creator capability

​Legacy MCP Install (Advanced > Tools)

​Output Formats

​Available Tools

​documents

​text

​paragraphs

​tables

​documentStyle

​headersFooters

​media

​namedRanges

​batch

​OAuth Session

​Tool Details

​documents (action: create)

​text (action: insert)

​text (action: replaceAll)

​tables (action: insert)

​media (action: insertImage)

​batch (action: update)

​Error Handling

​Common Issues

​External Resources

Google Docs API v1

Tool Agents

Prerequisites

Installation

Configuration

Authorize end-users

Available Instructions

Documents

Text

Paragraphs

Tables

Document Style

Headers, Footers & Footnotes

Media

Named Ranges

Batch

DSUL Examples

Create a Doc and populate it with a title + intro

Replace placeholders across an existing template

Insert a 3×4 table and merge the header row

Build a multi-step report atomically with `batchUpdate`

Plug into an Agent Creator capability

Legacy MCP Install (Advanced > Tools)

Output Formats

Available Tools

`documents`

`text`

`paragraphs`

`tables`

`documentStyle`

`headersFooters`

`media`

`namedRanges`

`batch`

OAuth Session

Tool Details

`documents` (action: `create`)

`text` (action: `insert`)

`text` (action: `replaceAll`)

`tables` (action: `insert`)

`media` (action: `insertImage`)

`batch` (action: `update`)

Error Handling

Common Issues

External Resources