# 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 cannot anchor a new comment to a live range, that anchor format is not public, so it appears at document level). action=reply adds a reply (needs comment_id + content). action=resolve closes the thread (needs comment_id; optional content posts a closing reply); action=reopen reactivates it. action=delete PERMANENTLY removes the comment and all its replies (needs comment_id) — deleting is final, resolving is the reversible way to close a thread. Get comment_id from list_comments. Requires a Drive scope on the OAuth token.

Agent View of the PolicyLayer registry record for `manage_comment`. HTML page: https://policylayer.com/tools/a1-x-tech-mcp-google-docs/manage-comment

## Facts

- Tool: `manage_comment`
- Server: Mcp Google Docs (`@a1-x-tech/mcp-google-docs`) — https://policylayer.com/tools/a1-x-tech-mcp-google-docs.md
- Install: `npx -y @a1-x-tech/mcp-google-docs`
- Homepage: https://github.com/A1-x-Tech/mcp-google-docs
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 5 (2 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `action` | string | yes | What to do with the document's comments. |
| `content` | string | no | create/reply: the comment text (plain text). Optional closing text for resolve/reopen. |
| `comment_id` | string | no | reply/resolve/reopen/delete: the comment thread to target (from list_comments). |
| `document_id` | string | yes | The document id — the long id from the document URL (docs.google.com/document/d/<documentId>/edit) or from create_document output. |
| `quoted_text` | string | no | create only: the passage of document text the comment refers to (shown as a quote). |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "manage_comment",
    "arguments": {
      "action": "<action>",
      "document_id": "<document_id>"
    }
  }
}
```

## Why manage_comment is rated Critical

An AI agent that decides to call manage_comment doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Mcp Google Docs is gone. There is no undo for destructive operations.

Risk signals: Accepts raw HTML/template content (content)

## Use case

AI agents call manage_comment to permanently remove resources in Mcp Google Docs, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp Google Docs:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "manage_comment"
  ]
}
```

## Other tools on Mcp Google Docs (26)

- `delete_range` — Destructive — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/delete-range.md
- `logout` — Destructive — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/logout.md
- `start_login` — Execute — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/start-login.md
- `style_paragraph` — Execute — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/style-paragraph.md
- `auth_status` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/auth-status.md
- `get_document` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/get-document.md
- `list_comments` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/list-comments.md
- `list_tabs` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/list-tabs.md
- `raw_request` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/raw-request.md
- `read_document_text` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/read-document-text.md
- `style_text` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/style-text.md
- `create_document` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/create-document.md
- `edit_table` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/edit-table.md
- `export_document` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/export-document.md
- `finish_login` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/finish-login.md
- `import_markdown` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/import-markdown.md
- `insert_break` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-break.md
- `insert_image` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-image.md
- `insert_table` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-table.md
- `insert_text` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-text.md
- `replace_all_text` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-all-text.md
- `replace_image` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-image.md
- `replace_range` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-range.md
- `set_client` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/set-client.md
- `set_paragraph_bullets` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/set-paragraph-bullets.md
- `setup_instructions` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/setup-instructions.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a1-x-tech-mcp-google-docs · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a1-x-tech-mcp-google-docs