xpath_query

THE RISK

High Risk

Why xpath_query needs a policy

This tool executes arbitrary XPath queries against DOCX document parts. While XPath is primarily a query language, executing arbitrary expressions against any part of the document structure constitutes an Execute-level action. The 'any DOCX part' scope and pre-bound namespaces suggest broad access to internal XML structures.

From the tool's definition "Run XPath against any DOCX part" — executes arbitrary XPath expressions against document internals

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

POLICY

How to control xpath_query

PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for xpath_query:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "xpath_query": {
      "limits": [
        {
          "counter": "xpath_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

xpath_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Docx tools

Destructive delete_column_from_table Delete a column (0-based) from every row of a table. Destructive delete_comment Delete a comment and remove its range markers from the document. Destructive delete_content_control Remove an SDT content control wrapper, keeping its content in place. Destructive delete_custom_property Delete a custom document property by name. Destructive delete_endnote Delete an endnote and its in-body reference. Destructive delete_field Remove a complete complex field (begin through end runs) from the document. Destructive delete_footer Delete a footer by location: default, first, or even. Destructive delete_footnote Delete a footnote and its in-body reference.

All 219 Docx tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Docx → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about xpath_query

What does the xpath_query tool do? +

Run XPath against any DOCX part. Pre-bound namespaces: w, w14, r, wp, a, mc. It is categorised as a Execute tool in the Docx MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on xpath_query? +

Register the Docx MCP server in PolicyLayer and add a rule for xpath_query: 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 xpath_query? +

xpath_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit xpath_query? +

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

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

xpath_query is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Docx tool call.

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

CHECK YOUR STACK →