Get predictive search results (autocomplete)
AI agents call predictive_search 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 search suggestions/predictions from Shopify's search index. It queries data without creating, modifying, deleting, or executing external operations. The autocomplete nature means it returns pre-computed or filtered suggestions based on input, with no side effects. This is a classic Read operation with minimal security risk.
From the tool's definition Tool name 'predictive_search' combined with description 'Get predictive search results (autocomplete)' indicates a retrieval operation. The word 'Get' in the description confirms data querying without modification.
Attacks that exploit this kind of access
Get predictive search results (autocomplete). 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 predictive_search: 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.
predictive_search 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 predictive_search 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 predictive_search. 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.
predictive_search 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 →