update_apply · Kb MCP: Risk & Policy

WHAT IT DOES

What update_apply does on Kb

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

WHY IT NEEDS A POLICY

Why update_apply needs a policy

The tool name 'update_apply' strongly implies a write operation that creates or modifies data (likely knowledge/notes) in the KB system. Without an explicit description, confidence is moderate; however, the semantic meaning of 'apply' combined with 'update' in a note-storage context points to a reversible modification rather than destruction or execution of arbitrary code.

From the tool's definition Tool name 'update_apply' suggests applying updates to stored knowledge or notes in the knowledge base system. The context of a 'shared context and learning foundation' with 'persistent knowledge' storage indicates this tool modifies data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_apply Rate-limited

update_apply 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": {
    "update_apply": {
      "limits": [
        {
          "counter": "update_apply_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 Kb, so you can run agents against it safely.

FAQ

Questions about update_apply

What does the update_apply tool do? +

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

How do I enforce a policy on update_apply? +

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

What risk level is update_apply? +

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

Can I rate-limit update_apply? +

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

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

update_apply is provided by the Kb MCP server (okash1n/kb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.