Call one downstream MCP tool with multiple argument sets.
AI agents invoke toolmux_batch to trigger actions in Mcp Toolmux. 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.
This tool executes downstream MCP tools in batch, meaning it can trigger any operation (read, write, destructive, financial) depending on which tool is called and with what arguments.
From the tool's definition 'Call one downstream MCP tool with multiple argument sets' — executes downstream MCP tools, potentially triggering arbitrary operations across multiple invocations
Attacks that exploit this kind of access
Call one downstream MCP tool with multiple argument sets. It is categorised as a Execute tool in the Mcp Toolmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Toolmux MCP server in PolicyLayer and add a rule for toolmux_batch: 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 Mcp Toolmux. Nothing to install.
toolmux_batch 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 toolmux_batch 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 toolmux_batch. 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.
toolmux_batch is provided by the Mcp Toolmux MCP server (mxz-dddd/mcp-toolmux). 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 →