register_self · Teammate MCP: Risk & Policy

WHAT IT DOES

What register_self does on Teammate

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

WHY IT NEEDS A POLICY

Why register_self needs a policy

The tool likely creates or modifies state by registering an entity in a system (Write category). Without a description, confidence is reduced. Severity is medium because registering could enable unauthorized agents to join communication channels, but the blast radius depends heavily on what 'registration' actually enables.

From the tool's definition Tool name is 'register_self' with an empty description. Based on context as part of a communication system between Claude and OpenAI Codex instances, 'register_self' most likely registers or enrolls the current instance in the communication system, creating a…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

register_self Rate-limited

register_self 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": {
    "register_self": {
      "limits": [
        {
          "counter": "register_self_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 Teammate, so you can run agents against it safely.

FAQ

Questions about register_self

What does the register_self tool do? +

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

How do I enforce a policy on register_self? +

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

What risk level is register_self? +

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

Can I rate-limit register_self? +

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

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

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