scan_documents · Lightrag MCP: Risk & Policy

WHAT IT DOES

What scan_documents does on Lightrag

AI agents invoke scan_documents to trigger actions in Lightrag. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why scan_documents needs a policy

The tool triggers an active scanning process rather than passively reading data. It causes the system to scan a directory and process documents, which constitutes executing an external operation with side effects (documents may be ingested, indexed, or queued for processing). This is an Execute-level action since it initiates a pipeline operation whose effects depend on what files are present.

From the tool's definition 'Trigger scanning process for new documents in the input directory' — initiates an external pipeline/process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_documents Rate-limited

scan_documents 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about scan_documents

What does the scan_documents tool do? +

Trigger scanning process for new documents in the input directory. It is categorised as a Execute tool in the Lightrag MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scan_documents? +

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

What risk level is scan_documents? +

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

Can I rate-limit scan_documents? +

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

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

scan_documents is provided by the Lightrag MCP server (lightrag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.