Get autocomplete suggestions for Open Food Facts taxonomy entries (brands, categories, labels, etc.).
AI agents call autocomplete to retrieve information from Open Food Facts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves autocomplete suggestions from a taxonomy database. It queries existing data and returns suggestions without creating, modifying, deleting, or executing any operations. The read-only nature and minimal impact on system state classify this as a Read risk with low severity.
From the tool's definition Tool name 'autocomplete' and description 'Get autocomplete suggestions' indicates retrieval of suggestion data with no modification or side effects.
Attacks that exploit this kind of access
Get autocomplete suggestions for Open Food Facts taxonomy entries (brands, categories, labels, etc.). It is categorised as a Read tool in the Open Food Facts MCP Server, which means it retrieves data without modifying state.
Register the Open Food Facts MCP server in PolicyLayer and add a rule for autocomplete: 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 Open Food Facts. Nothing to install.
autocomplete 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 autocomplete 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 autocomplete. 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.
autocomplete is provided by the Open Food Facts MCP server (openfoodfacts-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 →