Run dependent downstream MCP tool calls serially with input mapping.
AI agents invoke toolmux_pipeline 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 acts as an executor that chains multiple downstream MCP tool calls together. While it doesn't directly perform destructive or financial operations, it enables execution of arbitrary operations through downstream tools with input mapping control.
From the tool's definition Tool description states it can 'Run dependent downstream MCP tool calls serially with input mapping.' This enables execution of arbitrary downstream tools in sequence with data flow between them, which constitutes code/operation execution.
Attacks that exploit this kind of access
Run dependent downstream MCP tool calls serially with input mapping. 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_pipeline: 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_pipeline 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_pipeline 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_pipeline. 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_pipeline 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 →