AI agents call get_claude_config 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 reads and displays configuration data about registered MCP servers. It performs a query operation without modifying, deleting, or executing any infrastructure changes. The blast radius is minimal—an AI agent could learn about registered servers but cannot alter them or perform any destructive actions.
From the tool's definition Tool name 'get_claude_config' and description 'Get the Claude Desktop MCP server configuration. Shows all registered MCP servers.' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the Claude Desktop MCP server configuration. Shows all registered MCP servers. 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 get_claude_config: 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.
get_claude_config 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_claude_config 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_claude_config. 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_claude_config 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 →