List all collections, or list documents in one collection.
AI agents call vector_store_list to retrieve information from Vending Machine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about vector store collections and their documents without modifying, deleting, or executing anything. It has no side effects and poses minimal risk if misused by an agent—at worst, it exposes what data is stored in the vector store, which is an informational concern rather than a security threat.
From the tool's definition Tool name 'vector_store_list' and description 'List all collections, or list documents in one collection' indicate retrieval/query operations only. 'List' operations are explicitly Read category per guidelines.
Attacks that exploit this kind of access
List all collections, or list documents in one collection. It is categorised as a Read tool in the Vending Machine MCP Server, which means it retrieves data without modifying state.
Register the Vending Machine MCP server in PolicyLayer and add a rule for vector_store_list: 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 Vending Machine. Nothing to install.
vector_store_list 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 vector_store_list 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 vector_store_list. 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.
vector_store_list is provided by the Vending Machine MCP server (yokiidesu/vending-machine-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 →