add_memory · local-RAG-backend MCP: Risk & Policy

WHAT IT DOES

What add_memory does on local-RAG-backend

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

WHY IT NEEDS A POLICY

Why add_memory needs a policy

The tool name and context of a RAG backend with Neo4j graph storage suggest 'add_memory' creates or modifies knowledge graph data. This is reversible through sibling delete/clear operations, making it Write rather than Destructive. The empty description lowers confidence slightly from high to medium, but the server's document and relationship tracking purpose makes Write the clear categorization.

From the tool's definition Tool name 'add_memory' indicates creation or modification of memory data. Sibling tools include 'delete_entity_edge', 'delete_episode', and 'clear_graph', indicating this server manages persistent data structures (graph entities, relationships, episodes).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_memory Rate-limited

add_memory 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": {
    "add_memory": {
      "limits": [
        {
          "counter": "add_memory_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 local-RAG-backend, so you can run agents against it safely.

FAQ

Questions about add_memory

What does the add_memory tool do? +

add_memory. It is categorised as a Write tool in the local-RAG-backend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_memory? +

Register the local-RAG-backend MCP server in PolicyLayer and add a rule for add_memory: 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 local-RAG-backend. Nothing to install.

What risk level is add_memory? +

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

Can I rate-limit add_memory? +

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

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

add_memory is provided by the local-RAG-backend MCP server (suwa-sh/local-rag-backend). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.