Re-embed all memories in the vector database.
AI agents invoke reset_memories to trigger actions in Open WebUI MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers a bulk re-embedding operation across the entire vector database, which is a computational operation with broad side effects. It's not a simple read or write of a single record — it processes and rewrites all memory embeddings. This qualifies as Execute due to the external operation triggered.
From the tool's definition Re-embed all memories in the vector database
Documented attack patterns abuse exactly the kind of access reset_memories 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 reset_memories:
{
"version": "1",
"default": "deny",
"tools": {
"reset_memories": {
"limits": [
{
"counter": "reset_memories_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}reset_memories stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Re-embed all memories in the vector database. It is categorised as a Execute tool in the Open WebUI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Open WebUI MCP Server MCP server in PolicyLayer and add a rule for reset_memories: 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.
reset_memories is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the reset_memories 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 reset_memories. 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.
reset_memories 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.