List skills within a specific category. Returns skill names, descriptions, tags, and risk levels with pagination support. Use skills_browse_categories first to see valid category names. Args: - category: Category name (e.g.,
AI agents call skills_list_by_category to retrieve information from Skills 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 skills in a structured format. It performs no mutations, deletions, executions, or financial operations. The mention of pagination and the need to use skills_browse_categories first indicates a standard read-based navigation interface. The risk is minimal because misuse results only in reading data that was intended to be discovered and browsed.
From the tool's definition Tool 'lists skills within a specific category' and 'returns skill names, descriptions, tags, and risk levels' — these are query/retrieval operations with no side effects. The description explicitly uses 'list' and 'returns', indicating data retrieval only.
Attacks that exploit this kind of access
List skills within a specific category. Returns skill names, descriptions, tags, and risk levels with pagination support. Use skills_browse_categories first to see valid category names. Args: - category: Category name (e.g.,. It is categorised as a Read tool in the Skills MCP Server, which means it retrieves data without modifying state.
Register the Skills MCP server in PolicyLayer and add a rule for skills_list_by_category: 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 Skills. Nothing to install.
skills_list_by_category 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 skills_list_by_category 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 skills_list_by_category. 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.
skills_list_by_category is provided by the Skills MCP server (lucasromanzin/skills-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 →