Creates a initial knowledge base and dataset for the user.
AI agents use create_rag to create or update resources in RAGFlow MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RAGFlow MCP environment.
This tool creates new data objects (knowledge base and dataset) but does not irreversibly delete data, execute arbitrary code, move funds, or modify existing resources. The action is reversible (datasets and knowledge bases can typically be deleted or recreated). It falls squarely in the Write category: creates new, structured data.
From the tool's definition Tool name and description: 'Creates a initial knowledge base and dataset for the user.' The verb 'Creates' indicates the tool constructs new persistent data structures (knowledge base and dataset). This is reversible creation, not deletion.
Documented attack patterns abuse exactly the kind of access create_rag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAGFlow MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_rag:
{
"version": "1",
"default": "deny",
"tools": {
"create_rag": {
"limits": [
{
"counter": "create_rag_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_rag 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.
Creates a initial knowledge base and dataset for the user. It is categorised as a Write tool in the RAGFlow MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RAGFlow MCP server in PolicyLayer and add a rule for create_rag: 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 RAGFlow MCP. Nothing to install.
create_rag 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_rag 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_rag. 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_rag is provided by the RAGFlow MCP server (oraichain/ragflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAGFlow MCP, 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.
4 RAGFlow MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.