Retrieve the exact content of a specific template file. Run list-templates first to see available names. Use these templates verbatim instead of improvising.
AI agents call get-template to retrieve information from Metalsmith Plugin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns template file content without creating, modifying, deleting, executing code, or moving money. It is a straightforward data retrieval operation with minimal blast radius if misused by an agent.
From the tool's definition Tool description explicitly states 'Retrieve the exact content' of template files. This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Retrieve the exact content of a specific template file. Run list-templates first to see available names. Use these templates verbatim instead of improvising. It is categorised as a Read tool in the Metalsmith Plugin MCP Server, which means it retrieves data without modifying state.
Register the Metalsmith Plugin MCP server in PolicyLayer and add a rule for get-template: 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 Metalsmith Plugin. Nothing to install.
get-template 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 get-template 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 get-template. 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.
get-template is provided by the Metalsmith Plugin MCP server (metalsmith-plugin-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 →