# superdoc_comment

Manage document comment threads: create, read, update, and delete. To create a comment, first use superdoc_search to find the target text, then pass action "create" with the comment text and a target built from items[0].blocks. For a single-block match use {kind:"text", blockId: items[0].blocks[0].blockId, range: items[0].blocks[0].range}. For a cross-block match use {kind:"text", segments: items[0].blocks.map(b => ({blockId: b.blockId, range: b.range}))}. Do NOT use items[0].highlightRange (snippet-relative, not block-relative) or items[0].target (a SelectionTarget, not accepted by comments.create). For threaded replies, pass "parentId" with the parent comment ID. Action "list" returns all comments with optional pagination (limit, offset) and filtering (includeResolved:true to include resolved). Action "get" retrieves a single comment by ID. Action "update" changes comment text, re-anchors the thread, changes status to "resolved", or toggles the legacy sdcom:internal flag for v1 compatibility. Action "delete" removes a comment or reply by ID. Do NOT pass "ref", "id", or "parentId" when creating a new top-level comment; "action", "text", and "target" are required, while commentId (the v1 compatibility alias for externalId), externalId, author fields, and metadata are optional correlation fields. EXAMPLES: 1. {"action":"create","text":"Please review this section.","target":{"kind":"text","blockId":"<blockId>","range":{"start":5,"end":25}}} 2. {"action":"list","limit":20,"offset":0} 3. {"action":"update","id":"<commentId>","status":"resolved"} 4. {"action":"delete","id":"<commentId>"}

Agent View of the PolicyLayer registry record for `superdoc_comment`. HTML page: https://policylayer.com/tools/superdoc-mcp/superdoc-comment

## Facts

- Tool: `superdoc_comment`
- Server: Superdoc (`@superdoc/mcp`) — https://policylayer.com/tools/superdoc-mcp.md
- Install: `npx -y @superdoc/mcp`
- Homepage: https://www.npmjs.com/package/@superdoc/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 12 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | string | no | Required for actions 'delete', 'get'. |
| `side` | string | no | Optional side for the top-level trackedChangeId shorthand. Only for action 'create'. Omit for other actions. |
| `text` | object | no | Comment text content. Required for action 'create'. |
| `force` | boolean | no | Bypass confirmation checks. |
| `limit` | integer | no | Maximum number of comments to return. Only for action 'list'. Omit for other actions. |
| `story` | object | no | Optional story for the top-level trackedChangeId shorthand. Only for action 'create'. Omit for other actions. |
| `action` | string | yes | The action to perform. One of: create, delete, get, list, update. |
| `author` | string | no | Author display name. Defaults to the configured session author. Only for action 'create'. Omit for other actions. |
| `offset` | integer | no | Number of comments to skip for pagination. Only for action 'list'. Omit for other actions. |
| `status` | string | no | Set comment status. Use 'resolved' to resolve a comment, or 'active' to reopen a previously resolved comment (lifecycle inverse). Only for action 'update'. Omit |
| `target` | object | no | Text range to anchor the comment. Accepts either a single-block TextAddress {kind:'text', blockId, range}, a multi-segment TextTarget {kind:'text', segments:[{b |
| `authorId` | string | no | Stable caller-owned author id. Only for action 'create'. Omit for other actions. |

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": "superdoc_comment",
    "arguments": {
      "action": "<action>"
    }
  }
}
```

## Why superdoc_comment is rated Medium

An AI agent can call superdoc_comment faster than any human can review: one bad instruction and it creates or modifies resources in Superdoc by the hundred, each call as confident as the last.

Risk signals: High parameter count (23 properties)

## Use case

AI agents use superdoc_comment to create or update resources in Superdoc, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Superdoc environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Superdoc:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "superdoc_comment": {
      "limits": [
        {
          "counter": "superdoc_comment_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Superdoc (12)

- `superdoc_mutations` — Destructive — https://policylayer.com/tools/superdoc-mcp/superdoc-mutations.md
- `superdoc_table` — Destructive — https://policylayer.com/tools/superdoc-mcp/superdoc-table.md
- `superdoc_track_changes` — Destructive — https://policylayer.com/tools/superdoc-mcp/superdoc-track-changes.md
- `superdoc_format` — Execute — https://policylayer.com/tools/superdoc-mcp/superdoc-format.md
- `superdoc_get_content` — Read — https://policylayer.com/tools/superdoc-mcp/superdoc-get-content.md
- `superdoc_list` — Read — https://policylayer.com/tools/superdoc-mcp/superdoc-list.md
- `superdoc_search` — Read — https://policylayer.com/tools/superdoc-mcp/superdoc-search.md
- `superdoc_close` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-close.md
- `superdoc_create` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-create.md
- `superdoc_edit` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-edit.md
- `superdoc_open` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-open.md
- `superdoc_save` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-save.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=superdoc-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/superdoc-mcp