open_document

THE RISK

Low Risk

Why open_document needs a policy

Opening a document is a read operation; it retrieves the document contents without creating, modifying, or deleting anything. Severity is low as it only accesses local files, though path traversal misuse is a minor concern.

From the tool's definition 'Open an existing Word document' — opens/reads a file at the given path, no modification implied

Documented attack patterns abuse exactly the kind of access open_document gives an agent:

POLICY

How to control open_document

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 open_document:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "open_document": {}
  }
}

open_document is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Doc/docx — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Doc/docx tools

Destructive delete_paragraph Delete specified paragraph from document Parameters: - paragraph_index: Parag Destructive delete_table_row Delete a row from table Parameters: - table_index: Table index - row_inde Destructive delete_text Delete specified text from paragraph Parameters: - paragraph_index: Paragraph Write find_and_replace Find and replace text in the document Parameters: - find_text: Text to find Write search_and_replace Search and replace text in the document, providing detailed replacement information and pr Write add_heading Add heading to document Parameters: - text: Heading text - level: Heading Write add_page_break Add page break Write add_paragraph Add paragraph text to document Parameters: - text: Paragraph text content

All 23 Doc/docx tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about open_document

What does the open_document tool do? +

Open an existing Word document Parameters: - file_path: Path to the document to open. It is categorised as a Read tool in the Doc/docx MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on open_document? +

Register the Doc/docx MCP server in PolicyLayer and add a rule for open_document: 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.

What risk level is open_document? +

open_document is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit open_document? +

Yes. Add a rate_limit block to the open_document 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 open_document completely? +

Set action: deny in the PolicyLayer policy for open_document. 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 open_document? +

open_document 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.

Enforce policy on every Doc/docx tool call.

Start from Doc/docx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →