List all skill categories with their skill counts. Use this first to understand what types of skills are available before searching or listing. Returns a table of categories (e.g., architecture, data-ai, security) with the number of skills in each. Tip: After browsing categories, use skills_list_...
AI agents call skills_browse_categories 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 performs a simple query operation to enumerate and display skill categories and their counts. It has no capability to modify, execute, delete, or move data, making it a straightforward Read operation. The blast radius of misuse is minimal—an AI agent could only browse category metadata, not perform any consequential actions.
From the tool's definition Tool 'lists all skill categories with their skill counts' and 'returns a table of categories' — these are retrieval operations with no side effects, no code execution, and no data modification or deletion.
Attacks that exploit this kind of access
List all skill categories with their skill counts. Use this first to understand what types of skills are available before searching or listing. Returns a table of categories (e.g., architecture, data-ai, security) with the number of skills in each. Tip: After browsing categories, use skills_list_by_category to explore a specific category, or skills_search to find skills by keywords. 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_browse_categories: 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_browse_categories 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_browse_categories 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_browse_categories. 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_browse_categories 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 →