AI agents call get_server_info to retrieve information from Shell without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration and security settings from the server without modifying, executing, or deleting anything. It is a read-only operation that queries the server state. The low severity reflects that exposure of configuration details has limited blast radius compared to tools that modify or execute code.
From the tool's definition Tool name 'get_server_info' and description 'Get the current server configuration and security settings' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the current server configuration and security settings. It is categorised as a Read tool in the Shell MCP Server, which means it retrieves data without modifying state.
Register the Shell MCP server in PolicyLayer and add a rule for get_server_info: 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 Shell. Nothing to install.
get_server_info 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_server_info 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_server_info. 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_server_info is provided by the Shell MCP server (kg912/shell-mcp). 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 →