# superdoc_get_content

Read document content in various formats. Call this first in any workflow to understand document structure before making edits. Action "blocks" returns structured block data with nodeId, nodeType, textPreview, optional full text when includeText:true, formatting properties (fontFamily, fontSize, color, bold, underline, alignment), and ref handles for immediate use with superdoc_edit or superdoc_format. Paragraph-class blocks include tabCount, the number of U+0009 tabs in the complete text even if the 80-character preview trims or truncates them. If tabCount is positive, read includeText:true before editing; do not treat a preview space as proof that there is no tab. Its optional reviewMode selects final, original, or redline numbering metadata without filtering blocks. When you need to evaluate or rewrite existing paragraphs or clauses, prefer action "blocks" with includeText:true so you can identify the correct block and then target it by nodeId. Actions "text", "markdown", and "html" return compact strings. Actions "markdown_projection" and "html_projection" return detailed async projections with review modes, scopes, diagnostics, annotations, block maps, and optional source maps. Projection source targets use tracked coordinates and are valid only at evaluatedRevision; after any mutation, reproject before using them. Treat omitted or partially emitted annotations according to their status instead of guessing an anchor from rendered text. Action "info" returns document metadata: word count, paragraph count, page count, outline, available styles, and capability flags. The "blocks" action supports pagination via "offset" and "limit", filtering via "nodeTypes", and numbering projection via "reviewMode". Other actions ignore pagination and filtering parameters. This tool never modifies the document. Do NOT call superdoc_edit or superdoc_format without first reading blocks to get valid refs and formatting reference values. EXAMPLES: 1. {"action":"blocks"} 2. {"action":"blocks","includeText":true,"offset":0,"limit":20,"reviewMode":"final"} 3. {"action":"blocks","offset":0,"limit":20,"nodeTypes":["heading","paragraph"]} 4. {"action":"text"} 5. {"action":"info"} 6. {"action":"html_projection","reviewMode":"redline","includeSourceMap":true} 7. {"action":"markdown_projection","reviewMode":"original","scope":{"kind":"block","nodeType":"paragraph","nodeId":"paragraph-id"},"includeSourceMap":true}

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

## Facts

- Tool: `superdoc_get_content`
- 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: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 12 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `in` | object | no | Story scope. Defaults to document body when omitted. Use {kind:'story', storyType:'body'} for body, or other storyType values for headers, footers, footnotes, e |
| `limit` | number | no | Maximum blocks to return. Omit for all blocks. Only for action 'blocks'. Omit for other actions. |
| `scope` | object | no | Only for actions 'markdown_projection', 'html_projection'. Omit for other actions. |
| `action` | string | yes | The action to perform. One of: blocks, extract, html, html_projection, info, markdown, markdown_projection, text. |
| `offset` | number | no | Number of blocks to skip. Default: 0. Only for action 'blocks'. Omit for other actions. |
| `nodeIds` | array | no | Top-level block identities to match before pagination. Only for action 'blocks'. Omit for other actions. |
| `nodeTypes` | array | no | Filter by block types (e.g. ['paragraph', 'heading']). Omit for all types. Only for action 'blocks'. Omit for other actions. |
| `reviewMode` | string | no | Only for actions 'markdown_projection', 'html_projection', 'blocks'. Omit for other actions. |
| `session_id` | string | yes | Session ID from superdoc_open. |
| `textSearch` | object | no | Only for action 'blocks'. Omit for other actions. |
| `includeText` | boolean | no | When true, includes the full flattened block text in each block entry. Only for action 'blocks'. Omit for other actions. |
| `unflattenLists` | boolean | no | Deprecated and ignored by V2. V2 always emits canonical nested semantic lists. Only for action 'html'. 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_get_content",
    "arguments": {
      "action": "<action>",
      "session_id": "<session_id>"
    }
  }
}
```

## Why superdoc_get_content is rated Low

Even though superdoc_get_content only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: High parameter count (16 properties)

## Use case

AI agents call superdoc_get_content to retrieve information from Superdoc without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "superdoc_get_content": {}
  }
}
```

## 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_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_comment` — Write — https://policylayer.com/tools/superdoc-mcp/superdoc-comment.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