AI agents call read_tag to retrieve information from Ignition without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'read_tag' operation queries or retrieves tag values from an Ignition SCADA system with no side effects. Reading tags is a fundamental query operation that does not create, modify, or delete data. The presence of multiple read-only sibling tools (get_*, list_*) on the server confirms this classification pattern.
From the tool's definition Tool name 'read_tag' combined with server context listing 'get_tags' and other read-only tools (get_alarm, get_history, get_named_query, get_script, get_view, list_alarms, list_named_queries) indicates this retrieves tag data from Ignition SCADA without…
Attacks that exploit this kind of access
read_tag. It is categorised as a Read tool in the Ignition MCP Server, which means it retrieves data without modifying state.
Register the Ignition MCP server in PolicyLayer and add a rule for read_tag: 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 Ignition. Nothing to install.
read_tag 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 read_tag 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 read_tag. 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.
read_tag is provided by the Ignition MCP server (nodeblue-ai/ignition-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →