vector_store · MCP Roo Memory MCP: Risk & Policy

WHAT IT DOES

What vector_store does on MCP Roo Memory

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

WHY IT NEEDS A POLICY

Why vector_store needs a policy

This tool writes new vector embeddings into a Qdrant vector database. It creates persistent data but is reversible (data can be deleted later), placing it in the Write category. Misuse could result in polluting the knowledge graph with incorrect or malicious data, giving it medium severity.

From the tool's definition 'Store text with automatic vectorization into Qdrant' — the tool creates/writes data (text embeddings) into a vector store

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vector_store Rate-limited

vector_store 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": {
    "vector_store": {
      "limits": [
        {
          "counter": "vector_store_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 Roo Memory, so you can run agents against it safely.

FAQ

Questions about vector_store

What does the vector_store tool do? +

Store text with automatic vectorization into Qdrant. It is categorised as a Write tool in the MCP Roo Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vector_store? +

Register the MCP Roo Memory MCP server in PolicyLayer and add a rule for vector_store: 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 Roo Memory. Nothing to install.

What risk level is vector_store? +

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

Can I rate-limit vector_store? +

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

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

vector_store is provided by the MCP Roo Memory MCP server (mcasdfgf/mcp-roo-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.