Search for Yeoman templates
AI agents call yeoman_search_templates to retrieve information from Mcp Yeoman without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation to retrieve and list Yeoman templates from a registry or repository. It retrieves data without modifying, executing, or deleting anything. This is a classic Read operation. The low severity reflects that searching for templates poses minimal risk—it cannot execute code, modify systems, or cause financial harm.
From the tool's definition Tool name is 'yeoman_search_templates' and description states 'Search for Yeoman templates'. The verb 'search' and 'search for' indicate querying/retrieving information about available templates with no side effects.
Attacks that exploit this kind of access
Search for Yeoman templates. It is categorised as a Read tool in the Mcp Yeoman MCP Server, which means it retrieves data without modifying state.
Register the Mcp Yeoman MCP server in PolicyLayer and add a rule for yeoman_search_templates: 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 Yeoman. Nothing to install.
yeoman_search_templates 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 yeoman_search_templates 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 yeoman_search_templates. 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.
yeoman_search_templates is provided by the Mcp Yeoman MCP server (thirdstrandstudio/mcp-yeoman). 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 →