Update paragraph text while preserving the style structure of multiple runs. When a paragraph has multiple styled runs (e.g., bold + normal text), this tool distributes the new text across runs proportionally while keeping their original character styles. Strategy: - Distributes new text propor...
Single-target operation
Part of the Hwpx MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use update_paragraph_text_preserve_styles to create or modify resources in Hwpx. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call update_paragraph_text_preserve_styles repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Hwpx.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
update_paragraph_text_preserve_styles:
rules:
- action: allow
rate_limit:
max: 30
window: 60 See the full Hwpx policy for all 135 tools.
Agents calling write-class tools like update_paragraph_text_preserve_styles have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Update paragraph text while preserving the style structure of multiple runs. When a paragraph has multiple styled runs (e.g., bold + normal text), this tool distributes the new text across runs proportionally while keeping their original character styles. Strategy: - Distributes new text proportionally based on original run lengths - Preserves charPrIDRef (character style) of each run - If new text is longer, extends the last run - If original has no text, sets to first run Use this instead of update_paragraph_text when you need to maintain style formatting across multiple runs within a single paragraph. Example: Paragraph with "Hello" (bold) + " World" (normal) → update_paragraph_text_preserve_styles("Goodbye Universe") → Result: "Goodbye" (bold) + " Universe" (normal). It is categorised as a Write tool in the Hwpx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for update_paragraph_text_preserve_styles. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Hwpx MCP server.
update_paragraph_text_preserve_styles is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_paragraph_text_preserve_styles rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for update_paragraph_text_preserve_styles. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_paragraph_text_preserve_styles is provided by the Hwpx MCP server (hwpx-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.