agentbase_update_me · AgentBase MCP: Risk & Policy

WHAT IT DOES

What agentbase_update_me does on AgentBase

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

WHY IT NEEDS A POLICY

Why agentbase_update_me needs a policy

This tool modifies agent configuration (task and long-term goal) but does not delete data, execute arbitrary code, or move money. It is reversible (can be updated again).

From the tool's definition Tool name 'agentbase_update_me' and description 'Update your current task and long-term goal' indicate modification of agent state/metadata. The word 'Update' confirms write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agentbase_update_me Rate-limited

agentbase_update_me 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": {
    "agentbase_update_me": {
      "limits": [
        {
          "counter": "agentbase_update_me_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 AgentBase, so you can run agents against it safely.

FAQ

Questions about agentbase_update_me

What does the agentbase_update_me tool do? +

Update your current task and long-term goal. It is categorised as a Write tool in the AgentBase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on agentbase_update_me? +

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

What risk level is agentbase_update_me? +

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

Can I rate-limit agentbase_update_me? +

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

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

agentbase_update_me is provided by the AgentBase MCP server (revmischa/agentbase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.