knowledge_merge · Loom MCP: Risk & Policy

WHAT IT DOES

What knowledge_merge does on Loom

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

WHY IT NEEDS A POLICY

Why knowledge_merge needs a policy

This is a Write operation because it creates or modifies data reversibly. Consolidation merges multiple knowledge pages into one, which is a modification of data structure and content. It is not Destructive because consolidation is typically reversible and the intent is to unify rather than erase (though pre-merge state loss is a concern, the semantic action is combinatorial rather than deletion).

From the tool's definition Tool performs 'Consolidate 2+ knowledge pages into one canonical page' — this modifies existing data by merging multiple records into a single unified record.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knowledge_merge Rate-limited

knowledge_merge 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": {
    "knowledge_merge": {
      "limits": [
        {
          "counter": "knowledge_merge_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 Loom, so you can run agents against it safely.

FAQ

Questions about knowledge_merge

What does the knowledge_merge tool do? +

Consolidate 2+ knowledge pages into one canonical page. It is categorised as a Write tool in the Loom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on knowledge_merge? +

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

What risk level is knowledge_merge? +

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

Can I rate-limit knowledge_merge? +

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

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

knowledge_merge is provided by the Loom MCP server (jbarket/loom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.