Search and browse agent skills from mcpmarket.com.
AI agents call mcpmarket_skills to retrieve information from Mcp Mcpmarket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about agent skills available on mcpmarket.com. The operations (search, browse) have no side effects—they only retrieve or display data. No data is created, modified, deleted, or executed. This falls squarely into the Read category with low severity because misuse would only expose existing catalogued information.
From the tool's definition Tool name 'mcpmarket_skills' and description 'Search and browse agent skills' indicate query/discovery operations without modification. Verbs like 'search' and 'browse' are read-only operations.
Attacks that exploit this kind of access
Search and browse agent skills from mcpmarket.com. It is categorised as a Read tool in the Mcp Mcpmarket MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mcpmarket MCP server in PolicyLayer and add a rule for mcpmarket_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 Mcp Mcpmarket. Nothing to install.
mcpmarket_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 mcpmarket_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 mcpmarket_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.
mcpmarket_skills is provided by the Mcp Mcpmarket MCP server (xzeroone/mcp-mcpmarket). 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 →