Find paragraphs containing specified keyword and replace them and their surrounding content, keeping original position, format, and style Parameters: - keyword: Keyword to find - new_content: New content list, each element is a paragraph - section_range: Surrounding paragraph range to replace, de...
AI agents use edit_section_by_keyword to create or update resources in Doc/docx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Doc/docx environment.
This tool creates or modifies data reversibly (edit, update operations), which maps to the Write category. While it could potentially be misused to alter significant document sections (high severity due to broad impact via keyword matching and configurable range), it does not irreversibly delete data (not Destructive) nor execute arbitrary code (not Execute).
From the tool's definition The tool 'edit_section_by_keyword' modifies document content by finding paragraphs with a keyword and replacing 'them and their surrounding content' with new content. This is a reversible modification operation that changes existing data in the document.
Documented attack patterns abuse exactly the kind of access edit_section_by_keyword gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Doc/docx, and nothing reaches the server without passing your rules. This is the rule we recommend for edit_section_by_keyword:
{
"version": "1",
"default": "deny",
"tools": {
"edit_section_by_keyword": {
"limits": [
{
"counter": "edit_section_by_keyword_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}edit_section_by_keyword stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find paragraphs containing specified keyword and replace them and their surrounding content, keeping original position, format, and style Parameters: - keyword: Keyword to find - new_content: New content list, each element is a paragraph - section_range: Surrounding paragraph range to replace, default is 3. It is categorised as a Write tool in the Doc/docx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Doc/docx MCP server in PolicyLayer and add a rule for edit_section_by_keyword: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Doc/docx. Nothing to install.
edit_section_by_keyword 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 edit_section_by_keyword rule in your PolicyLayer 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 PolicyLayer policy for edit_section_by_keyword. 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.
edit_section_by_keyword is provided by the Doc/docx MCP server (meterlong/mcp-doc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Doc/docx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Doc/docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.