reprocess_failed · Lightrag MCP: Risk & Policy

WHAT IT DOES

What reprocess_failed does on Lightrag

AI agents invoke reprocess_failed 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 reprocess_failed needs a policy

This tool re-triggers a processing pipeline on documents already in the system. It does not merely read data, nor does it create/modify new data directly or delete anything. It executes an operational action (reprocessing) whose side effects depend on the state of the documents and the pipeline logic. Since it could modify document state and trigger downstream operations, Execute is the most appropriate category.

From the tool's definition "Reprocess failed and pending documents" — triggers reprocessing of existing documents

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reprocess_failed Rate-limited

reprocess_failed 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": {
    "reprocess_failed": {
      "limits": [
        {
          "counter": "reprocess_failed_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 reprocess_failed

What does the reprocess_failed tool do? +

Reprocess failed and pending documents. 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 reprocess_failed? +

Register the Lightrag MCP server in PolicyLayer and add a rule for reprocess_failed: 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 reprocess_failed? +

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

Can I rate-limit reprocess_failed? +

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

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

reprocess_failed 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.