AI agents use update_tool 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.
Updating tool code is a reversible write operation that can change tool behavior and potentially introduce malicious logic. However, it does not delete data (ruling out Destructive) and does not directly execute code itself (ruling out Execute). The impact is high because modified tools could then be executed by other agents or users, creating a significant blast radius for administrative systems.
From the tool's definition Tool description states 'Update a tool's name or code' — this modifies existing tool definitions and their executable code.
Documented attack patterns abuse exactly the kind of access update_tool 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 update_tool:
{
"version": "1",
"default": "deny",
"tools": {
"update_tool": {
"limits": [
{
"counter": "update_tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_tool 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.
Update a tool's name or code. 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 update_tool: 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.
update_tool 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 update_tool 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 update_tool. 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.
update_tool 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.