Retrieve a specific skill by its ID
AI agents call alfred_get_skill to retrieve information from Alfred MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves/queries data (a skill) by ID without modifying, deleting, or executing anything. This is a standard read operation with minimal blast radius—an AI agent misusing this tool can only access skill information, not create, modify, or delete skills or trigger their execution.
From the tool's definition Tool name 'alfred_get_skill' and description 'Retrieve a specific skill by its ID' indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Retrieve a specific skill by its ID. It is categorised as a Read tool in the Alfred MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Alfred MCP Server MCP server in PolicyLayer and add a rule for alfred_get_skill: 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 Alfred MCP Server. Nothing to install.
alfred_get_skill 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 alfred_get_skill 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 alfred_get_skill. 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.
alfred_get_skill is provided by the Alfred MCP Server MCP server (lumberjack-so/alfred-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 →