AI agents invoke message_workers to trigger actions in Claude Team MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name suggests sending messages to worker sessions. Given the server context — orchestrating Claude Code sessions in iTerm2 terminals with parallel task execution — messaging workers likely triggers actions or commands in those sessions. The description is empty, lowering confidence, but the server context implies this could cause worker sessions to execute arbitrary tasks.
From the tool's definition Tool name 'message_workers' on a server that 'spawns, monitors, and messages worker sessions' in terminal windows running Claude Code instances
Documented attack patterns abuse exactly the kind of access message_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 message_workers:
{
"version": "1",
"default": "deny",
"tools": {
"message_workers": {
"limits": [
{
"counter": "message_workers_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}message_workers stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
message_workers. It is categorised as a Execute tool in the Claude Team MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Team MCP Server MCP server in PolicyLayer and add a rule for message_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.
message_workers is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the message_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 message_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.
message_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.