AI agents call trace_tag to retrieve information from Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Tracing tags in SCADA/PLC systems retrieves and queries the flow of industrial control signals across projects without modifying state. This is fundamentally a Read operation (trace, correlate, analyze data).
From the tool's definition Tool name 'trace_tag' with no description; inferred from context to trace signal chains in industrial SCADA/PLC systems (Ignition and Studio 5000)
Attacks that exploit this kind of access
trace_tag. It is categorised as a Read tool in the Bridge MCP Server, which means it retrieves data without modifying state.
Register the Bridge MCP server in PolicyLayer and add a rule for trace_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 Bridge. Nothing to install.
trace_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 trace_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 trace_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.
trace_tag is provided by the Bridge MCP server (nodeblue-ai/bridge-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 →