ingest_current_directory · Omni Rag MCP: Risk & Policy

WHAT IT DOES

What ingest_current_directory does on Omni Rag

AI agents invoke ingest_current_directory to trigger actions in Omni Rag. 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 ingest_current_directory needs a policy

Triggering an indexing process is an Execute-category action: it runs an operation that processes files and writes index data. It is not purely a read, and while it writes index state, the primary action is executing an indexing pipeline. Severity is medium because misuse could cause unintended indexing of sensitive directories or resource exhaustion, but it does not delete or expose data directly.

From the tool's definition 'Manually trigger indexing' — the tool actively triggers an indexing operation over the current directory, which is an external operation with side effects (building/updating an index). Marked as Deprecated in favor of 'ingest'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ingest_current_directory Rate-limited

ingest_current_directory 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": {
    "ingest_current_directory": {
      "limits": [
        {
          "counter": "ingest_current_directory_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 Omni Rag, so you can run agents against it safely.

FAQ

Questions about ingest_current_directory

What does the ingest_current_directory tool do? +

[Deprecated: use 'ingest'] Manually trigger indexing. It is categorised as a Execute tool in the Omni Rag MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ingest_current_directory? +

Register the Omni Rag MCP server in PolicyLayer and add a rule for ingest_current_directory: 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 Omni Rag. Nothing to install.

What risk level is ingest_current_directory? +

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

Can I rate-limit ingest_current_directory? +

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

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

ingest_current_directory is provided by the Omni Rag MCP server (suyash2013/codebase-rag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.