AI agents use cmux_group_members to create or update resources in Cmux — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cmux environment.
This tool modifies workspace group membership and structure (add, remove, set-anchor), which are reversible organizational changes. No code execution, deletion of data, or financial operations are involved. Misuse could disrupt workspace organization but changes can be undone.
From the tool's definition 'add a workspace to a group, remove a workspace from its group, or set-anchor to make a member the group'
Attacks that exploit this kind of access
add a workspace to a group, remove a workspace from its group (group inferred from membership), or set-anchor to make a member the group. It is categorised as a Write tool in the Cmux MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cmux MCP server in PolicyLayer and add a rule for cmux_group_members: 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 Cmux. Nothing to install.
cmux_group_members is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cmux_group_members 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 cmux_group_members. 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.
cmux_group_members is provided by the Cmux MCP server (puchkoff/cmux-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →