AI agents call discover_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.
The tool retrieves information about active worker sessions managed by the MCP server, analogous to listing or querying state. No description is provided, but the name and context of sibling tools (monitor, check, examine, list) suggest this is a read-only discovery/enumeration operation with no side effects. This aligns with the 'Read' category for data retrieval operations.
From the tool's definition Tool name 'discover_workers' indicates discovery/enumeration of existing worker sessions; consistent with sibling tools like 'list_workers' and 'examine_worker' which are read-only operations for monitoring parallel Claude Code sessions.
Documented attack patterns abuse exactly the kind of access discover_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 discover_workers:
{
"version": "1",
"default": "deny",
"tools": {
"discover_workers": {}
}
}discover_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.
discover_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 discover_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.
discover_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 discover_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 discover_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.
discover_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.