Find nodes by display name pattern (supports wildcards)
AI agents call find_by_display_name to retrieve information from OPC UA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the OPC UA node tree to locate nodes matching a display name pattern. It has no side effects—it only retrieves and filters existing metadata. The wildcard search capability does not elevate it beyond Read classification, as it remains a passive information retrieval operation with no impact on system state or data integrity.
From the tool's definition Tool description states 'Find nodes by display name pattern' with wildcard support. It searches and retrieves node metadata without modifying data or executing operations. Sibling tools ('read_value', 'find_by_browse_name') confirm a Read-only query pattern.
Documented attack patterns abuse exactly the kind of access find_by_display_name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OPC UA MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find_by_display_name:
{
"version": "1",
"default": "deny",
"tools": {
"find_by_display_name": {}
}
}find_by_display_name is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find nodes by display name pattern (supports wildcards). It is categorised as a Read tool in the OPC UA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OPC UA MCP Server MCP server in PolicyLayer and add a rule for find_by_display_name: 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 OPC UA MCP Server. Nothing to install.
find_by_display_name is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find_by_display_name 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 find_by_display_name. 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.
find_by_display_name is provided by the OPC UA MCP Server MCP server (vogler75/opcua-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OPC UA 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.
3 OPC UA MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.