Create a new knowledge base for RAG.
AI agents use create_knowledge_base to create or update resources in Open WebUI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Open WebUI MCP Server environment.
This tool creates a new resource (knowledge base) without destroying or moving money, and does not execute arbitrary code or commands. While it affects system state, creation is reversible through deletion or modification.
From the tool's definition Tool name and description indicate it 'Create[s] a new knowledge base' — a data creation operation that modifies the system state reversibly.
Documented attack patterns abuse exactly the kind of access create_knowledge_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Open WebUI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_knowledge_base:
{
"version": "1",
"default": "deny",
"tools": {
"create_knowledge_base": {
"limits": [
{
"counter": "create_knowledge_base_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_knowledge_base 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 knowledge base for RAG. It is categorised as a Write tool in the Open WebUI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Open WebUI MCP Server MCP server in PolicyLayer and add a rule for create_knowledge_base: 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 WebUI MCP Server. Nothing to install.
create_knowledge_base 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 create_knowledge_base 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 create_knowledge_base. 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.
create_knowledge_base is provided by the Open WebUI MCP Server MCP server (troylar/open-webui-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Open WebUI 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.
82 Open WebUI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.