create_docx

Create a new blank Word document.

SERVERDocx SOURCEandrew82106/llm_docx_agent_mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/andrew82106-llm-docx-agent-mcp/create-docx.md

WHAT IT DOES

What create_docx does on Docx

AI agents use create_docx 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.

RISK

Why create_docx is rated Medium

Creating a new document is a write operation—it generates new data and persists it to storage, but is fully reversible (the file can be deleted). There is no code execution, destructive action, or financial implication. The blast radius is minimal since the operation only creates an empty document with no side effects. Severity is low because accidental misuse (creating unwanted blank documents) causes minimal harm.

From the tool's definition Tool name is 'create_docx' and description states 'Create a new blank Word document.' This is a document creation operation that modifies the file system by adding a new file.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_docx safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Docx, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_docx, this is the rule to start with:

create_docx Rate-limited

create_docx 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_docx": {
      "limits": [
        {
          "counter": "create_docx_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Docx, apply this rule, and every create_docx call is checked against it from then on.

FAQ

Questions about create_docx

What does the create_docx tool do? +

Create a new blank Word document. It is categorised as a Write tool in the Docx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_docx? +

Register the Docx MCP server in PolicyLayer and add a rule for create_docx: 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 Docx. Nothing to install.

What risk level is create_docx? +

create_docx is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_docx? +

Yes. Add a rate_limit block to the create_docx 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.

How do I block create_docx completely? +

Set action: deny in the PolicyLayer policy for create_docx. 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.

What MCP server provides create_docx? +

create_docx is provided by the Docx MCP server (andrew82106/llm_docx_agent_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Docx, and thousands of servers like it.

This server

All 24 Docx tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →