ingest_text · Rag MCP: Risk & Policy

WHAT IT DOES

What ingest_text does on Rag

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

WHY IT NEEDS A POLICY

Why ingest_text needs a policy

This tool writes new content into the knowledge base by ingesting raw text. It is reversible (the sibling tool 'delete_document' exists), so it falls under Write rather than Destructive. Misuse could pollute the knowledge base with incorrect or malicious information, giving it a medium severity.

From the tool's definition 'Ingest raw text into the knowledge base' — creates new data in the knowledge base from raw text input.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ingest_text Rate-limited

ingest_text 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": {
    "ingest_text": {
      "limits": [
        {
          "counter": "ingest_text_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 Rag, so you can run agents against it safely.

FAQ

Questions about ingest_text

What does the ingest_text tool do? +

Ingest raw text into the knowledge base. It is categorised as a Write tool in the Rag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ingest_text? +

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

What risk level is ingest_text? +

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

Can I rate-limit ingest_text? +

Yes. Add a rate_limit block to the ingest_text 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_text completely? +

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

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