Lists or reads reference files for a specific skill. Many skills have 5-7 deep-dive reference docs in their references/ subdirectory. Args: - skill_name (string): Exact skill name - filename (string, optional): Specific reference filename to read. If omitted, lists all references. Returns: List o...
AI agents call rules_get_skill_references 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 tool performs read-only operations: listing files in a references directory or retrieving file contents. It has no side effects, cannot modify data, and is purely a retrieval mechanism for documentation.
From the tool's definition Tool description states 'Lists or reads reference files' with optional filename parameter. Returns either 'List of reference filenames, or full content of a specific reference file.' No modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Lists or reads reference files for a specific skill. Many skills have 5-7 deep-dive reference docs in their references/ subdirectory. Args: - skill_name (string): Exact skill name - filename (string, optional): Specific reference filename to read. If omitted, lists all references. Returns: List of reference filenames, or full content of a specific reference file. 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_get_skill_references: 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_get_skill_references 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_get_skill_references 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_get_skill_references. 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_get_skill_references 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 →