Fetch files from a theme
AI agents call get_theme_files to retrieve information from Shopify Graphql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves theme files from a Shopify store without altering them. Fetching read-only data poses minimal risk—it does not create, modify, delete, or execute anything. The primary risk is information disclosure of theme source code, which is typically low severity in a Shopify context since theme code is not usually sensitive.
From the tool's definition Tool name 'get_theme_files' and description 'Fetch files from a theme' indicate retrieval of existing theme data with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Fetch files from a theme. It is categorised as a Read tool in the Shopify Graphql MCP Server, which means it retrieves data without modifying state.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for get_theme_files: 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 Shopify Graphql. Nothing to install.
get_theme_files 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_theme_files 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_theme_files. 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_theme_files is provided by the Shopify Graphql MCP server (uvu-store/shopify-graphql-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 →