system.listTools
AI agents call system.listTools to retrieve information from Universal MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A 'listTools' operation typically enumerates available tools on the server, which is a read-only introspective action. No data is modified, executed, or deleted. The empty description lowers confidence slightly, but the naming convention is clear. Severity is low as exposing a tool list has minimal blast radius — at worst it reveals server capabilities.
From the tool's definition Tool name is 'system.listTools' — description is empty and uninformative, lowering confidence. However, 'listTools' strongly implies listing/querying available tools, which is a read operation with no side effects.
Attacks that exploit this kind of access
system.listTools. It is categorised as a Read tool in the Universal MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Universal MCP Server MCP server in PolicyLayer and add a rule for system.listTools: 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 Universal MCP Server. Nothing to install.
system.listTools 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 system.listTools 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 system.listTools. 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.
system.listTools is provided by the Universal MCP Server MCP server (ysharma79/mcp-server). 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 →