runDebuggerMode
Activate debugger mode to identify and resolve issues in applications directly from the BrowserTools MCP server, enabling precise analysis and troubleshooting of browser interactions.
Instructions
Run debugger mode to debug an issue in our application
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- The handler function for the 'runDebuggerMode' tool. It returns static text instructions guiding the AI on how to debug issues in the application, including steps for reflection, logging, analysis, and avoiding audits during debugging.async () => ({ content: [ { type: "text", text: ` Please follow this exact sequence to debug an issue in our application: 1. Reflect on 5-7 different possible sources of the problem 2. Distill those down to 1-2 most likely sources 3. Add additional logs to validate your assumptions and track the transformation of data structures throughout the application control flow before we move onto implementing the actual code fix 4. Use the "getConsoleLogs", "getConsoleErrors", "getNetworkLogs" & "getNetworkErrors" tools to obtain any newly added web browser logs 5. Obtain the server logs as well if accessible - otherwise, ask me to copy/paste them into the chat 6. Deeply reflect on what could be wrong + produce a comprehensive analysis of the issue 7. Suggest additional logs if the issue persists or if the source is not yet clear 8. Once a fix is implemented, ask for approval to remove the previously added logs Note: DO NOT run any of our audits (runAccessibilityAudit, runPerformanceAudit, runBestPracticesAudit, runSEOAudit, runNextJSAudit) when in debugging mode unless explicitly asked to do so or unless you switch to audit mode. `, }, ], }) );
- browser-tools-mcp/mcp-server.ts:1287-1312 (registration)Registration of the 'runDebuggerMode' tool on the MCP server using server.tool(). The handler is defined inline and provides debugging instructions.server.tool( "runDebuggerMode", "Run debugger mode to debug an issue in our application", async () => ({ content: [ { type: "text", text: ` Please follow this exact sequence to debug an issue in our application: 1. Reflect on 5-7 different possible sources of the problem 2. Distill those down to 1-2 most likely sources 3. Add additional logs to validate your assumptions and track the transformation of data structures throughout the application control flow before we move onto implementing the actual code fix 4. Use the "getConsoleLogs", "getConsoleErrors", "getNetworkLogs" & "getNetworkErrors" tools to obtain any newly added web browser logs 5. Obtain the server logs as well if accessible - otherwise, ask me to copy/paste them into the chat 6. Deeply reflect on what could be wrong + produce a comprehensive analysis of the issue 7. Suggest additional logs if the issue persists or if the source is not yet clear 8. Once a fix is implemented, ask for approval to remove the previously added logs Note: DO NOT run any of our audits (runAccessibilityAudit, runPerformanceAudit, runBestPracticesAudit, runSEOAudit, runNextJSAudit) when in debugging mode unless explicitly asked to do so or unless you switch to audit mode. `, }, ], }) );