load_document · DocNav- MCP: Risk & Policy

WHAT IT DOES

What load_document does on DocNav-MCP

AI agents use load_document to create or update resources in DocNav-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DocNav-MCP environment.

WHY IT NEEDS A POLICY

Why load_document needs a policy

Loading a document registers it within the DocNav system for subsequent operations. This creates state (a document record accessible to other tools like navigate_section, read_section, etc.), which is a Write action. It does not delete, execute code, or involve finances. Severity is medium because a malicious actor could load sensitive or malicious documents into the agent's context.

From the tool's definition "Load a document for navigation and analysis" — loading a document implies creating a new document entry/session in the system, which is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_document Rate-limited

load_document 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": {
    "load_document": {
      "limits": [
        {
          "counter": "load_document_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DocNav-MCP, so you can run agents against it safely.

FAQ

Questions about load_document

What does the load_document tool do? +

Load a document for navigation and analysis. It is categorised as a Write tool in the DocNav-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on load_document? +

Register the DocNav- MCP server in PolicyLayer and add a rule for load_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 DocNav-MCP. Nothing to install.

What risk level is load_document? +

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

Can I rate-limit load_document? +

Yes. Add a rate_limit block to the load_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 load_document completely? +

Set action: deny in the PolicyLayer policy for load_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 load_document? +

load_document is provided by the DocNav- MCP server (shenyimings/docnav-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.