# update_paragraph

A write tool on the Docx MCP server.

Agent View of the PolicyLayer registry record for `update_paragraph`. HTML page: https://policylayer.com/tools/securityronin-docx-mcp/update-paragraph

## Facts

- Tool: `update_paragraph`
- Server: Docx (`securityronin/docx-mcp`) — https://policylayer.com/tools/securityronin-docx-mcp.md
- Homepage: https://github.com/SecurityRonin/docx-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "update_paragraph",
    "arguments": {}
  }
}
```

## Why update_paragraph is rated Medium

This tool modifies document content reversibly (paragraphs can be edited again or deleted), consistent with Write category. Severity is medium because uncontrolled modifications to documents could corrupt content or overwrite important text, but the effect is confined to a single document and fully reversible.

From the tool's own definition: "Tool name 'update_paragraph' paired with server purpose of 'creating and editing Microsoft Word (.docx) documents'. Sibling tools include add_paragraph, add_heading, add_table—all Write operations."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Docx (218)

- `delete_column_from_table` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-column-from-table.md
- `delete_comment` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-comment.md
- `delete_content_control` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-content-control.md
- `delete_custom_property` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-custom-property.md
- `delete_endnote` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-endnote.md
- `delete_field` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-field.md
- `delete_footer` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-footer.md
- `delete_footnote` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-footnote.md
- `delete_header` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-header.md
- `delete_image` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-image.md
- `delete_paragraph` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-paragraph.md
- `delete_section_break` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-section-break.md
- `delete_style` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-style.md
- `delete_table` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-table.md
- `delete_table_row` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-table-row.md
- `delete_text` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/delete-text.md
- `flatten_document` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/flatten-document.md
- `remove_bookmark` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/remove-bookmark.md
- `remove_watermark` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/remove-watermark.md
- `scrub_pii` — Destructive — https://policylayer.com/tools/securityronin-docx-mcp/scrub-pii.md
- `compare_documents` — Execute — https://policylayer.com/tools/securityronin-docx-mcp/compare-documents.md
- `xpath_query` — Execute — https://policylayer.com/tools/securityronin-docx-mcp/xpath-query.md
- `audit_document` — Read — https://policylayer.com/tools/securityronin-docx-mcp/audit-document.md
- `check_accessibility` — Read — https://policylayer.com/tools/securityronin-docx-mcp/check-accessibility.md
- `compare_contracts` — Read — https://policylayer.com/tools/securityronin-docx-mcp/compare-contracts.md
- `diff_to_text` — Read — https://policylayer.com/tools/securityronin-docx-mcp/diff-to-text.md
- `export_markdown` — Read — https://policylayer.com/tools/securityronin-docx-mcp/export-markdown.md
- `generate_change_summary` — Read — https://policylayer.com/tools/securityronin-docx-mcp/generate-change-summary.md
- `get_alt_text` — Read — https://policylayer.com/tools/securityronin-docx-mcp/get-alt-text.md
- `get_body_text` — Read — https://policylayer.com/tools/securityronin-docx-mcp/get-body-text.md
- …and 188 more: https://policylayer.com/tools/securityronin-docx-mcp.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=securityronin-docx-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/securityronin-docx-mcp