AI agents call flowise_query_vector_store to retrieve information from Flowise without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a vector store, which is fundamentally a data query operation. The word 'retrieval' and 'query' indicate read-only access with no side effects. While 'Execute' might seem applicable due to the word 'Execute' in the description, the context makes clear this is executing a query (read operation), not executing arbitrary code or commands.
From the tool's definition Tool description states 'Execute a retrieval query on a document store's vector store' — retrieval is a read operation that queries and returns data without modifying or deleting it.
Attacks that exploit this kind of access
Execute a retrieval query on a document store's vector store. It is categorised as a Read tool in the Flowise MCP Server, which means it retrieves data without modifying state.
Register the Flowise MCP server in PolicyLayer and add a rule for flowise_query_vector_store: 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 Flowise. Nothing to install.
flowise_query_vector_store 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 flowise_query_vector_store 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 flowise_query_vector_store. 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.
flowise_query_vector_store is provided by the Flowise MCP server (julidir/flowise-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 →