// SCAN REPORT

Mcp Google Docs

27 tools. 20 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 4 Oct 2026

20 can modify or destroy data

7 read-only

27 tools total

Community server · catalogue entry checked 20/09/2026 · full schemas captured for 22 of 27 tools

How to control Mcp Google Docs ↓

TOOL MAP

What Mcp Google Docs exposes to your agents

Read (7) Write / Execute (17) Destructive / Financial (3)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Mcp Google Docs costs in tokens

7,620 tokens of tool definitions, loaded on every request

3.8% of a 200k context window

582 heaviest tool: style_text

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Google Docs tools

Destructive · Critical delete_range Deletes the content in [start_index, end_index) — text, inline images, whole tables or any mix, as long as the range does not cut across a t Destructive · High logout Revokes the stored token at Google (oauth2.googleapis.com/revoke) and deletes the local credentials file. Tokens supplied via env variables Destructive · High manage_comment Manages comment threads via the Drive API. action=create adds a NEW comment (needs content; optional quoted_text cites a passage — the API c Execute · Medium start_login First step of connecting from the chat, without editing config files or restarting the client. Returns authorizeUrl — show it to the user as

20 of Mcp Google Docs's 27 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Google Docs

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Google Docs, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_range": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_document": {
    "limits": [
      {
        "counter": "create_document_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "auth_status": {
    "limits": [
      {
        "counter": "auth_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Google Docs — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP GOOGLE DOCS →

Instant setup, no code required.

FULL CATALOGUE

All 27 Mcp Google Docs tools

DESTRUCTIVE 3 tools

Destructive delete_range Deletes the content in [start_index, end_index) — text, inline images, whole tables or any mix, as long as the Destructive logout Revokes the stored token at Google (oauth2.googleapis.com/revoke) and deletes the local credentials file. Toke Destructive manage_comment Manages comment threads via the Drive API. action=create adds a NEW comment (needs content; optional quoted_te

EXECUTE 2 tools

Execute start_login First step of connecting from the chat, without editing config files or restarting the client. Returns authori Execute style_paragraph Applies paragraph formatting to every paragraph overlapping [start_index, end_index): named_style (normal_text

WRITE 15 tools

Write create_document Creates a new Google Doc and returns its documentId. Without markdown it calls documents.create, which accepts Write edit_table Inserts or deletes a row/column of an existing table. The table is addressed by table_start_index — the table Write export_document Exports the document via Drive. Text formats (markdown, txt, html) are returned inline as the tool result — fo Write finish_login Second step: confirms the browser consent finished, saves the tokens to an owner-only file and verifies the lo Write import_markdown REPLACES the ENTIRE document content with the given Markdown via Drive conversion — the Markdown round-trip wr Write insert_break Inserts a break at an index (or at the end of the body when index is omitted). kind=page starts a new page; ki Write insert_image Inserts an inline image fetched from a PUBLIC URL at an index (or at the end of the body when index is omitted Write insert_table Inserts an empty rows x columns table at an index, or at the end of the body when index is omitted. Fill the c Write insert_text Inserts plain text at an index (UTF-16 code units; body content starts at index 1 — get indexes from read_docu Write replace_all_text Replaces EVERY occurrence of a literal string (no regex) across the whole document, or only in the tabs named Write replace_image Replaces an existing image's contents with a new image from a public URL, keeping the original's size and posi Write replace_range Replaces the content in [start_index, end_index) with new text — one atomic batchUpdate that deletes the range Write set_client Saves the OAuth client credentials from the JSON file downloaded from Google Cloud Console ('Download JSON' on Write set_paragraph_bullets Turns the paragraphs overlapping [start_index, end_index) into a list, or removes their bullets with remove=tr Write setup_instructions Step-by-step checklist for connecting this server to Google: creating a Google Cloud project and a Desktop-app

READ 7 tools

Read auth_status Shows whether this server is connected to Google: token presence and source (env variables or a stored in-chat Read get_document Returns the raw Docs API document: title, documentId, revisionId, per-tab body with every structural element's Read list_comments Lists the document's comment threads via the Drive API: for each comment its id, content, author displayName, Read list_tabs Returns the document's tab tree without content: tabId, title, position index and nested childTabs. Use the ta Read raw_request Escape hatch to call any Google Docs API v1 path directly, for requests the typed tools don't cover — e.g. a b Read read_document_text Returns the document as compact readable blocks, per tab: each paragraph with its text, start/end indexes (UTF Read style_text Applies character formatting to [start_index, end_index): bold, italic, underline, strikethrough, small_caps,

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Google Docs

Can an AI agent delete data through the Mcp Google Docs MCP server? +

Yes. The Mcp Google Docs server exposes 3 destructive tools including delete_range, logout, manage_comment. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Google Docs? +

The Mcp Google Docs server has 15 write tools including create_document, edit_table, export_document. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Google Docs.

How many tools does the Mcp Google Docs MCP server expose? +

27 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on Mcp Google Docs? +

Register the Mcp Google Docs MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Google Docs tool call.

Deterministic rules across all 27 Mcp Google Docs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP GOOGLE DOCS →

Instant setup, no code required.

27 Mcp Google Docs tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Mcp Google Docs's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →