AI agents call list_servers to retrieve information from Mcp Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about proxied MCP servers without modifying, deleting, or executing any operations. It is a read-only operation that simply enumerates available servers, making it a straightforward Read category tool with low severity since it only discloses the list of available backend servers.
From the tool's definition Tool name 'list_servers' and description 'List all proxied MCP servers available in this proxy' indicate it retrieves/queries information about available servers with no side effects.
Attacks that exploit this kind of access
List all proxied MCP servers available in this proxy. It is categorised as a Read tool in the Mcp Proxy MCP Server, which means it retrieves data without modifying state.
Register the Mcp Proxy MCP server in PolicyLayer and add a rule for list_servers: 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 Proxy. Nothing to install.
list_servers 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 list_servers 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 list_servers. 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.
list_servers is provided by the Mcp Proxy MCP server (shengxiao20/mcp-proxy-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 →