wavexis_start_combined_trace
Start a combined trace capturing screenshots, network, and console (W8).
This record as markdown: /tools/wavexis-mcp/wavexis-start-combined-trace.md
What wavexis_start_combined_trace does on Wavexis
AI agents invoke wavexis_start_combined_trace to trigger actions in Wavexis. 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.
Why wavexis_start_combined_trace is rated High
This tool starts a tracing/monitoring operation in a browser context, which is a triggered action that causes the browser to begin capturing data. While it does not execute user code directly, it initiates browser automation instrumentation—a form of Execute activity. The action is reversible (tracing can be stopped), so it does not rise to Destructive.
From the tool's definition "Start a combined trace capturing screenshots, network, and console" — initiates browser tracing/monitoring operations that trigger external side effects (screenshot capture, network interception, console logging) whose outcomes depend on runtime state.
Attacks that exploit this kind of access
The rule that runs wavexis_start_combined_trace safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Wavexis, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For wavexis_start_combined_trace, this is the rule to start with:
wavexis_start_combined_trace 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Wavexis, apply this rule, and every wavexis_start_combined_trace call is checked against it from then on.
Questions about wavexis_start_combined_trace
Start a combined trace capturing screenshots, network, and console (W8). It is categorised as a Execute tool in the Wavexis MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wavexis MCP server in PolicyLayer and add a rule for wavexis_start_combined_trace: 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 Wavexis. Nothing to install.
wavexis_start_combined_trace 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 wavexis_start_combined_trace 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 wavexis_start_combined_trace. 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.
wavexis_start_combined_trace is provided by the Wavexis MCP server (MathiasPaulenko/wavexis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Wavexis, and thousands of servers like it.
Across the catalogue