start_shadow_index · Vault Memory MCP: Risk & Policy

WHAT IT DOES

What start_shadow_index does on Vault Memory

AI agents invoke start_shadow_index to trigger actions in Vault Memory. 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 start_shadow_index needs a policy

Backfilling embeddings is a computational task that triggers indexing logic, modifies internal indexes, and potentially consumes resources. While not destructive (indexes can be rebuilt) or financial, it executes a defined operation whose scope depends on arguments ('every' suggests it operates over a collection).

From the tool's definition Tool name 'start_shadow_index' and description 'Backfill embeddings for a secondary (shadow) model over every' indicates triggering a background indexing operation that processes data and creates computational artifacts (embeddings).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_shadow_index Rate-limited

start_shadow_index 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": {
    "start_shadow_index": {
      "limits": [
        {
          "counter": "start_shadow_index_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 Vault Memory, so you can run agents against it safely.

FAQ

Questions about start_shadow_index

What does the start_shadow_index tool do? +

Backfill embeddings for a secondary (shadow) model over every. It is categorised as a Execute tool in the Vault Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_shadow_index? +

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

What risk level is start_shadow_index? +

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

Can I rate-limit start_shadow_index? +

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

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

start_shadow_index is provided by the Vault Memory MCP server (owrede/vault-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.