AI agents call get_loaded_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 retrieves state information about loaded MCP servers. It has no side effects and does not execute code, modify data, delete resources, or move money. The empty description lowers confidence slightly, but the name pattern aligns clearly with Read operations (compare to sibling tools like 'list_installed_mcp_servers', 'list_available_servers', 'list_all_tools').
From the tool's definition Tool name 'get_loaded_servers' indicates a query/retrieval operation. Description is empty, but the name strongly suggests listing or retrieving information about currently loaded servers without modification.
Attacks that exploit this kind of access
get_loaded_servers. 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 get_loaded_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.
get_loaded_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 get_loaded_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 get_loaded_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.
get_loaded_servers is provided by the MCP Proxy MCP server (lizthedeveloper/mcp_proxy). 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 →