findAndReplaceInDoc
Find and replace text across a Google Document. Dry-run mode counts matches exactly across body, tables, headers, footers, and footnotes. On zero matches the response explains the likeliest lookalike cause (non-breaking spaces, curly quotes, HTML entities, case). For multi-tab docs, specify tabId...
This record as markdown: /tools/ark7-google-drive-mcp/findandreplaceindoc.md
What findAndReplaceInDoc does on Google Drive
AI agents use findAndReplaceInDoc to create or update resources in Google Drive, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Drive environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
tabId | string | — | Optional. Tab ID to scope replacements to (from listDocumentTabs). If omitted, replaces across all tabs. |
dryRun | boolean | — | Only count matches, do not modify the document (default: false). Respects tabId scoping. |
account | string | — | Alias of the Google account to target. Optional — defaults to the session/global default account, or the sole authenticated account. Run manage_accounts list to |
findText | string | Yes | Text to find |
matchCase | boolean | — | Case-sensitive match (default: false) |
documentId | string | Yes | The document ID |
replaceText | string | Yes | Replacement text |
ifRevisionId | string | — | Optional optimistic lock: a revisionId from readGoogleDoc, getGoogleDocContent, getGoogleDocContentPaginated, or getDocumentInfo. The write fails cleanly if the |
expectedCount | number | — | Optional safety guard: the exact number of occurrences you expect to replace. Counted before writing; on a mismatch the call aborts without modifying the docume |
Parameters from the server's own tool schema.
Why findAndReplaceInDoc is rated Medium
Modifies document content by replacing text, but this is a reversible write operation.
From the tool's definition Find and replace text across a Google Document
Attacks that exploit this kind of access
The rule that runs findAndReplaceInDoc safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Google Drive, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For findAndReplaceInDoc, this is the rule to start with:
findAndReplaceInDoc stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Google Drive, apply this rule, and every findAndReplaceInDoc call is checked against it from then on.
Questions about findAndReplaceInDoc
Find and replace text across a Google Document. Dry-run mode counts matches exactly across body, tables, headers, footers, and footnotes. On zero matches the response explains the likeliest lookalike cause (non-breaking spaces, curly quotes, HTML entities, case). For multi-tab docs, specify tabId to scope replacements to a single tab. When replaceText contains a newline, the write is always locked to the revision its matches were located in — even without an explicit ifRevisionId — since the compiled batch targets indices from that read; a concurrent edit fails the call instead of landing at the wrong offsets. It is categorised as a Write tool in the Google Drive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
findAndReplaceInDoc accepts 9 parameters: tabId, dryRun, account, findText, matchCase, documentId, replaceText, ifRevisionId, expectedCount. Required: findText, documentId, replaceText. The full parameter table on this page comes from the server's own tool schema.
Register the Google Drive MCP server in PolicyLayer and add a rule for findAndReplaceInDoc: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google Drive. Nothing to install.
findAndReplaceInDoc is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the findAndReplaceInDoc rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for findAndReplaceInDoc. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
findAndReplaceInDoc is provided by the Google Drive MCP server (@ark7/google-drive-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Google Drive, and thousands of servers like it.
This server
Across the catalogue