Lists all 484 skills with names and descriptions, read from the manifest (fast — no filesystem scan). Optionally filter by category or keyword. Args: - filter (string, optional): Filter by name or description keyword (case-insensitive) Returns: Formatted skill list with descriptions.
AI agents call rules_list_skills to retrieve information from Claude Rules MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward query/list operation that retrieves metadata about available skills from a manifest. It has no side effects, does not execute code or modify data, and poses minimal risk if misused—an AI agent querying this tool would only retrieve informational data about skill definitions.
From the tool's definition Tool 'lists all 484 skills with names and descriptions' and 'read from the manifest'. The description explicitly states it performs a read-only retrieval operation with optional filtering by keyword.
Attacks that exploit this kind of access
Lists all 484 skills with names and descriptions, read from the manifest (fast — no filesystem scan). Optionally filter by category or keyword. Args: - filter (string, optional): Filter by name or description keyword (case-insensitive) Returns: Formatted skill list with descriptions. It is categorised as a Read tool in the Claude Rules MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Rules MCP Server MCP server in PolicyLayer and add a rule for rules_list_skills: 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 Claude Rules MCP Server. Nothing to install.
rules_list_skills 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 rules_list_skills 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 rules_list_skills. 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.
rules_list_skills is provided by the Claude Rules MCP Server MCP server (jeremykenedy/claude-rules-mcp-server). 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 →