re_embed_all · Ogham MCP: Risk & Policy

WHAT IT DOES

What re_embed_all does on Ogham

AI agents invoke re_embed_all to trigger actions in Ogham. 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 re_embed_all needs a policy

The name implies a bulk operation that re-processes all stored data through an embedding model (likely pgvector embeddings given the server context). This is an Execute-category action as it triggers a potentially expensive external operation (re-embedding all memories) that modifies stored vector representations.

From the tool's definition Tool name 're_embed_all' suggests re-generating embeddings for all stored memories; description is empty and uninformative.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

re_embed_all Rate-limited

re_embed_all 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": {
    "re_embed_all": {
      "limits": [
        {
          "counter": "re_embed_all_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 Ogham, so you can run agents against it safely.

FAQ

Questions about re_embed_all

What does the re_embed_all tool do? +

re_embed_all. It is categorised as a Execute tool in the Ogham MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on re_embed_all? +

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

What risk level is re_embed_all? +

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

Can I rate-limit re_embed_all? +

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

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

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