ingest_data · Mcp Local Rag MCP: Risk & Policy

WHAT IT DOES

What ingest_data does on Mcp Local Rag

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

WHY IT NEEDS A POLICY

Why ingest_data needs a policy

This tool writes/creates data into the RAG system by ingesting content and can overwrite existing content via re-ingestion. It modifies the document store reversibly (content can be deleted or re-ingested), placing it firmly in the Write category. Misuse could pollute the knowledge base with incorrect or malicious content, warranting medium severity.

From the tool's definition Ingest in-memory content as a string... The source identifier enables re-ingestion to update existing content

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ingest_data Rate-limited

ingest_data 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_data": {
      "limits": [
        {
          "counter": "ingest_data_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 Mcp Local Rag, so you can run agents against it safely.

FAQ

Questions about ingest_data

What does the ingest_data tool do? +

Ingest in-memory content as a string (use ingest_file for files on disk). The source identifier enables re-ingestion to update existing content. Returns { filePath, chunkCount, timestamp, fileTitle }. It is categorised as a Write tool in the Mcp Local 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_data? +

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

What risk level is ingest_data? +

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

Can I rate-limit ingest_data? +

Yes. Add a rate_limit block to the ingest_data 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_data completely? +

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

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