AI agents call list_workers to retrieve information from Claude Team MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about existing worker sessions. While the description is empty, the name and context from related tools (polling, examining, discovering workers) clearly suggest it queries state without modifying it. The blast radius of misuse is minimal—an agent can only gain visibility into running sessions, not alter or delete them.
From the tool's definition Tool name 'list_workers' combined with sibling tools like 'discover_workers', 'check_idle_workers', and 'examine_worker' indicates query/inspection functionality. The verb 'list' is consistently associated with retrieval operations that have no side effects.
Documented attack patterns abuse exactly the kind of access list_workers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Team MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_workers:
{
"version": "1",
"default": "deny",
"tools": {
"list_workers": {}
}
}list_workers is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_workers. It is categorised as a Read tool in the Claude Team MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP Server MCP server in PolicyLayer and add a rule for list_workers: 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 Claude Team MCP Server. Nothing to install.
list_workers is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_workers 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.
Set action: deny in the PolicyLayer policy for list_workers. 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.
list_workers is provided by the Claude Team MCP Server MCP server (martian-engineering/maniple). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Team MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 Claude Team MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.