Search downstream MCP tools and return compressed tool summaries.
AI agents call toolmux_search_tools to retrieve information from Mcp Toolmux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries information about available tools from downstream MCP servers. It performs a read-only search operation that returns summaries without modifying, executing, deleting, or financially impacting any systems. The operation is informational and has no side effects beyond data retrieval.
From the tool's definition Tool name contains 'search' and description states 'Search downstream MCP tools and return compressed tool summaries' — a query operation with no side effects.
Attacks that exploit this kind of access
Search downstream MCP tools and return compressed tool summaries. It is categorised as a Read tool in the Mcp Toolmux MCP Server, which means it retrieves data without modifying state.
Register the Mcp Toolmux MCP server in PolicyLayer and add a rule for toolmux_search_tools: 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_search_tools 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 toolmux_search_tools 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_search_tools. 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_search_tools 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 →