AI agents call list_mcp_servers to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about MCP server registrations from Claude Desktop configuration. It performs no modification, deletion, or execution of external operations—it is a simple information query with no side effects. The blast radius of misuse is minimal; disclosure of MCP server configurations poses a low risk in typical scenarios, though it could inform reconnaissance in a broader attack.
From the tool's definition Tool name 'list_mcp_servers' and description 'List all MCP servers registered in Claude Desktop config with their details' indicate a retrieval operation that queries configuration data.
Attacks that exploit this kind of access
List all MCP servers registered in Claude Desktop config with their details. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for list_mcp_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 Homelab. Nothing to install.
list_mcp_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_mcp_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_mcp_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_mcp_servers is provided by the Homelab MCP server (myraffy/homelab-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 →