Create a new vector store
AI agents use vector-store-create to create or update resources in Universal OpenAI Vector Store MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Universal OpenAI Vector Store MCP Server environment.
Creating a vector store creates a new resource with reversible consequences (it can be deleted via vector-store-delete). This is a Write operation—it modifies the state of the system by introducing a new entity, but the action is not irreversible or destructive.
From the tool's definition Tool name 'vector-store-create' and description 'Create a new vector store' indicate this creates a new persistent data structure in OpenAI's vector store system.
Documented attack patterns abuse exactly the kind of access vector-store-create gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Universal OpenAI Vector Store MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for vector-store-create:
{
"version": "1",
"default": "deny",
"tools": {
"vector-store-create": {
"limits": [
{
"counter": "vector-store-create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} vector-store-create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new vector store. It is categorised as a Write tool in the Universal OpenAI Vector Store MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Universal OpenAI Vector Store MCP Server MCP server in PolicyLayer and add a rule for vector-store-create: 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 Universal OpenAI Vector Store MCP Server. Nothing to install.
vector-store-create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the vector-store-create 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-create. 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-create is provided by the Universal OpenAI Vector Store MCP Server MCP server (jezweb/openai-vector-assistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Universal OpenAI Vector Store MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Universal OpenAI Vector Store MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.