{"report":"{\"v\":1,\"package\":\"browser-devtools-mcp\",\"version\":\"0.9.1\",\"ranAt\":\"2026-11-16T11:27:24.904Z\",\"install\":{\"ok\":true,\"bin\":\"browser-devtools-mcp\",\"integrity\":\"sha512-n7pJkNBFp5bGc9TpxzQjaTWVkHWNtpnSuyFOvuzQxueoR6rTseDnjRlm53bRC0qPRmY9kxMjAhnIV79ej6WJBA==\",\"deps\":245,\"scripts\":[\"@playwright/browser-chromium\",\"@playwright/browser-firefox\",\"@playwright/browser-webkit\",\"better-sqlite3\",\"browser-devtools-mcp\",\"protobufjs\",\"sharp\"],\"bins\":[\"browser-devtools-mcp\",\"node-devtools-mcp\",\"backend-devtools-mcp\",\"browser-devtools-cli\",\"node-devtools-cli\",\"backend-devtools-cli\"],\"license\":\"Elastic-2.0\",\"repository\":\"https://github.com/serkan-ozal/browser-devtools-mcp.git\"},\"start\":{\"ok\":true,\"ms\":635,\"serverName\":\"browser-devtools-mcp\",\"serverVersion\":\"0.9.1\",\"protocol\":\"2025-06-18\",\"stderr\":\"\\nTelemetry is enabled by default to help improve this tool.\\nRun with --no-telemetry for CLI and set TELEMETRY_ENABLE=false for MCP Servers to disable.\\n\\n\"},\"tools\":[{\"name\":\"a11y_take-aria-snapshot\",\"description\":\"ARIA snapshot of the page or a scoped element. Returns a tree with refs (e1, e2, ...) and a refs map.\\nUse refs in interaction tools: selector \\\"e1\\\" or \\\"@e1\\\" to click/fill that element. Output includes URL, title, and YAML tree.\\nRefs are valid until next snapshot or navigation. interactiveOnly: only interactive elements get refs; omit for content roles (headings, etc.) too.\\ncursorInteractive: true adds refs for clickable elements without ARIA (e.g. div with cursor:pointer/onclick).\\nUse with a11y_take-ax-tree-snapshot for full UI analysis.\",\"params\":[\"selector\",\"interactiveOnly\",\"maxDepth\",\"compact\",\"cursorInteractive\"]},{\"name\":\"a11y_take-ax-tree-snapshot\",\"description\":\"Combines Chromium AX tree with runtime visual diagnostics (bounding box, visibility, viewport).\\nUse to detect: elements with role/name but hidden or off-screen; layout/geometry issues; overlap/occlusion (enable checkOcclusion).\\nWhen investigating UI/layout or when clicks fail on seemingly visible elements, set checkOcclusion:true—it uses elementFromPoint()\\nat center+corners to find what is actually on top. boundingBox is from getBoundingClientRect() (viewport coords; layout box only).\\nselectorHint is best-effort (data-testid/data-selector/id). Use with a11y_take-aria-snapshot for full UI analysis.\",\"params\":[\"roles\",\"includeStyles\",\"includeRuntimeVisual\",\"checkOcclusion\",\"onlyVisible\",\"onlyInViewport\",\"textPreviewMaxLength\",\"styleProperties\"]},{\"name\":\"content_get-as-html\",\"description\":\"\\nGets the HTML content of the current page. \\nBy default, all <script> tags are removed from the output unless \\\"removeScripts\\\" is explicitly set to \\\"false\\\".\\n        \",\"params\":[\"selector\",\"removeScripts\",\"removeComments\",\"removeStyles\",\"removeMeta\",\"cleanHtml\",\"minify\",\"maxLength\"]},{\"name\":\"content_get-as-text\",\"description\":\"Gets the visible text content of the current page.\",\"params\":[\"selector\",\"maxLength\"]},{\"name\":\"content_save-as-pdf\",\"description\":\"Saves the current page as a PDF file.\",\"params\":[\"outputPath\",\"name\",\"format\",\"printBackground\",\"margin\"]},{\"name\":\"content_start-recording\",\"description\":\"Starts video recording of the browser page.\\nRecording captures all page interactions until content_stop-recording is called.\\nUses Playwright's native screencast API — works in all modes (headless, headed, persistent, CDP attach).\\nOnly supported on Chromium-based browsers.\",\"params\":[\"outputDir\",\"name\"]},{\"name\":\"content_stop-recording\",\"description\":\"Stops video recording of the browser page and saves the video file.\\nMust be called after content_start-recording. The video is saved as a WebM file.\",\"params\":[]},{\"name\":\"content_take-screenshot\",\"description\":\"Takes a screenshot of the current page or a specific element.\\nDo NOT use for page structure—use ARIA/AX snapshots instead.\\nUse only for visual verification (design check, visual bug, contrast, layout).\\nScreenshot is saved to disk; use includeBase64 only when the file cannot be read from the returned path (e.g. remote, container).\",\"params\":[\"outputPath\",\"name\",\"selector\",\"fullPage\",\"type\",\"quality\",\"includeBase64\",\"annotate\",\"annotateContent\",\"annotateCursorInteractive\"]},{\"name\":\"debug_status\",\"description\":\"\\nReturns the current debugging status including:\\n- Whether debugging is enabled\\n- Source map status\\n- Exceptionpoint state\\n- Count of tracepoints, logpoints, and watches\\n- Snapshot statistics\\n        \",\"params\":[]},{\"name\":\"debug_resolve-source-location\",\"description\":\"\\nResolves a generated/bundled code location to its original source via source maps.\\nUseful for translating minified stack traces or bundle line numbers to original TypeScript/JavaScript source.\\n\\nRequires a page with debugging context (debugging is auto-enabled on first use).\\nInput: generated script URL, line, column (1-based).\\nOutput: original source path, line, column when a source map is available.\\n        \",\"params\":[\"url\",\"line\",\"column\"]},{\"name\":\"debug_put-tracepoint\",\"description\":\"\\nPuts a non-blocking tracepoint at the specified location.\\nWhen hit, a snapshot of the call stack and local variables is captured \\nautomatically without pausing execution.\\n\\nThe urlPattern matches script URLs. Special characters are auto-escaped.\\nExamples:\\n- \\\"app.js\\\" matches scripts containing \\\"app.js\\\"\\n- \\\"bundle.min.js\\\" matches scripts containing \\\"bundle.min.js\\\"\\n\\nDO NOT escape characters yourself (e.g., don't use \\\"app\\\\.js\\\").\\n\\nReturns resolvedLocations: number of scripts where the tracepoint was set.\\nIf 0, the pattern didn't match any loaded scripts.\\n        \",\"params\":[\"urlPattern\",\"lineNumber\",\"columnNumber\",\"condition\",\"hitCondition\"]},{\"name\":\"debug_remove-probe\",\"description\":\"Removes a tracepoint, logpoint, or watch expression by ID.\\n`type`: `tracepoint`, `logpoint`, or `watch`. `id`: the probe or watch ID (from list-probes).\",\"params\":[\"type\",\"id\"]},{\"name\":\"debug_list-probes\",\"description\":\"Lists tracepoints, logpoints, and/or watch expressions. Optional `types`: array of `tracepoint`, `logpoint`, `watch`. If omitted or empty, returns all.\",\"params\":[\"types\"]},{\"name\":\"debug_clear-probes\",\"description\":\"Removes tracepoints, logpoints, and/or watch expressions. Optional `types`: array of `tracepoint`, `logpoint`, `watches`. If omitted or empty, clears all.\",\"params\":[\"types\"]},{\"name\":\"debug_put-logpoint\",\"description\":\"\\nPuts a logpoint at the specified location.\\nWhen the logpoint is hit, the logExpression is evaluated and the result \\nis captured in the snapshot's logResult field.\\n\\nLogpoints are lightweight - they only capture the log expression result,\\nNOT call stack or watch expressions. Use tracepoints for full debug context.\\n\\nurlPattern matches script URLs (e.g., \\\"app.js\\\"). Auto-escaped, do not add backslashes.\\n\\nlogExpression: a single JavaScript expression (e.g. \\\"user.name\\\", \\\"JSON.stringify({ a, b })\\\", or \\\"{ discountAmount, finalAmount, n }\\\"). Object literals are supported; for maximum compatibility prefer a single variable or JSON.stringify(...).\\n\\nReturns resolvedLocations: 0 means pattern didn't match any loaded scripts.\\n        \",\"params\":[\"urlPattern\",\"lineNumber\",\"logExpression\",\"columnNumber\",\"condition\",\"hitCondition\"]},{\"name\":\"debug_put-exceptionpoint\",\"description\":\"\\nSets the exception tracepoint state:\\n- \\\"none\\\": Don't capture on exceptions\\n- \\\"uncaught\\\": Capture only on uncaught exceptions\\n- \\\"all\\\": Capture on all exceptions (caught and uncaught)\\n\\nWhen an exception occurs, a snapshot is captured with exception details.\\n        \",\"params\":[\"state\"]},{\"name\":\"debug_get-probe-snapshots\",\"description\":\"Retrieves snapshots captured by tracepoints, logpoints, and/or exceptionpoints.\\nOptional `types`: array of `tracepoint`, `logpoint`, `exceptionpoint`. If omitted or empty, returns all.\\nResponse fields: `tracepointSnapshots`, `logpointSnapshots`, `exceptionpointSnapshots`.\\nOptional `probeId` filters tracepoint or logpoint snapshots; `fromSequence` and `limit` apply per type.\\nOutput trimming: by default only the top 5 call stack frames are returned, only `local` scope(s) are included, and variables per scope are capped at 20. Override with maxCallStackDepth, includeScopes, maxVariablesPerScope.\",\"params\":[\"types\",\"probeId\",\"fromSequence\",\"limit\",\"maxCallStackDepth\",\"includeScopes\",\"maxVariablesPerScope\"]},{\"name\":\"debug_clear-probe-snapshots\",\"description\":\"Clears snapshots captured by tracepoints, logpoints, and/or exceptionpoints.\\nOptional `types`: array of `tracepoint`, `logpoint`, `exceptionpoint`. If omitted or empty, clears all.\\nOptional `probeId`: clear only snapshots for this probe (for tracepoint/logpoint).\",\"params\":[\"types\",\"probeId\"]},{\"name\":\"debug_add-watch\",\"description\":\"\\nAdds a watch expression to be evaluated at every breakpoint hit.\\nWatch expression results are included in the snapshot's watchResults field.\\n\\nExamples:\\n- \\\"user.name\\\"\\n- \\\"this.state\\\"\\n- \\\"items.length\\\"\\n- \\\"JSON.stringify(config)\\\"\\n\\nWatch expressions are evaluated in the context of the paused frame.\\n        \",\"params\":[\"expression\"]},{\"name\":\"interaction_click\",\"description\":\"Clicks an element. Accepts selector or ref (e.g. e1, @e1). Set waitForNavigation: true when the click opens a new page — waits for navigation then for network idle so snapshot/screenshot see full content.\",\"params\":[\"selector\",\"timeoutMs\",\"waitForNavigation\",\"waitForTimeoutMs\"]},{\"name\":\"interaction_drag\",\"description\":\"Drags an element to a target location. Accepts CSS selectors or refs (e.g. e1, @e1) from the last ARIA snapshot.\",\"params\":[\"sourceSelector\",\"targetSelector\",\"timeoutMs\"]},{\"name\":\"interaction_fill\",\"description\":\"Fills out an input field. Accepts a CSS selector or a ref from the last ARIA snapshot (e.g. e1, @e1).\",\"params\":[\"selector\",\"value\",\"timeoutMs\"]},{\"name\":\"interaction_hover\",\"description\":\"Hovers an element on the page. Accepts a CSS selector or a ref from the last ARIA snapshot (e.g. e1, @e1).\",\"params\":[\"selector\",\"timeoutMs\"]},{\"name\":\"interaction_press-key\",\"description\":\"Presses a keyboard key with optional \\\"hold\\\" and auto-repeat behavior.\\n\\nKey facts:\\n- keyboard.press(key, { delay }) does NOT trigger OS-style auto-repeat.\\n- Some UI behaviors (especially scrolling) require repeated keydown events.\\n- Use repeat=true + holdMs to approximate real keyboard holding.\\n\\nExecution logic:\\n- If selector is provided, the element is focused first.\\n- If holdMs is omitted or repeat=false:\\n  → a single keyboard.press() is executed.\\n- If holdMs is provided AND repeat=true:\\n  → keyboard.press() is called repeatedly until holdMs elapses.\",\"params\":[\"key\",\"selector\",\"holdMs\",\"repeat\",\"repeatIntervalMs\",\"timeoutMs\"]},{\"name\":\"interaction_resize-viewport\",\"description\":\"Resizes the PAGE VIEWPORT using Playwright viewport emulation (page.setViewportSize).\\n\\nThis affects:\\n- window.innerWidth / window.innerHeight\\n- CSS media queries (responsive layouts)\\n- Layout, rendering and screenshots\\n\\nNotes:\\n- This does NOT resize the OS-level browser window.\\n- Runtime switching to viewport=null (binding to real window size) is not supported by Playwright.\\n  If you need real window-driven responsive behavior, start the BrowserContext with viewport: null\\n  and use the window resize tool instead.\",\"params\":[\"width\",\"height\"]},{\"name\":\"interaction_resize-window\",\"description\":\"Resizes the REAL BROWSER WINDOW (OS-level window) for the current page using Chrome DevTools Protocol (CDP).\\n\\nThis tool works best on Chromium-based browsers (Chromium/Chrome/Edge).\\nIt is especially useful in headful sessions when you run with viewport emulation disabled (viewport: null),\\nso the page layout follows the OS window size.\\n\\nImportant:\\n- If Playwright viewport emulation is enabled (viewport is NOT null), resizing the OS window may not change page layout.\\n- On non-Chromium browsers (Firefox/WebKit), CDP is not available and this tool will fail.\",\"params\":[\"width\",\"height\",\"state\"]},{\"name\":\"interaction_select\",\"description\":\"Select an option in a dropdown. Accepts a CSS selector or a ref from the last ARIA snapshot (e.g. e1, @e1).\",\"params\":[\"selector\",\"value\",\"timeoutMs\"]},{\"name\":\"interaction_scroll\",\"description\":\"Scrolls the page viewport or a specific scrollable element.\\n\\nModes:\\n- 'by': Scrolls by a relative delta (dx/dy) from the current scroll position.\\n- 'to': Scrolls to an absolute scroll position (x/y).\\n- 'top': Scrolls to the very top.\\n- 'bottom': Scrolls to the very bottom.\\n- 'left': Scrolls to the far left.\\n- 'right': Scrolls to the far right.\\n\\nUse this tool to:\\n- Reveal content below the fold\\n- Jump to the top/bottom without knowing exact positions\\n- Bring elements into view before clicking\\n- Inspect lazy-loaded content that appears on scroll\",\"params\":[\"mode\",\"selector\",\"dx\",\"dy\",\"x\",\"y\",\"behavior\"]},{\"name\":\"navigation_go-back-or-forward\",\"description\":\"\\nNavigates to the previous or next page in history.\\n- `direction: \\\"back\\\"` — previous page in history.\\n- `direction: \\\"forward\\\"` — next page in history.\\n\\nIn case of multiple redirects, the navigation will resolve with the response of the last redirect.\\nIf cannot go back/forward, returns empty response.\\n\\nBy default (includeSnapshot: true), an ARIA snapshot with refs is returned. Use `snapshotOptions` for `interactiveOnly` (default false) and `cursorInteractive` (default false), same as a11y_take-aria-snapshot.\\n\\nWhen `includeScreenshot: true`, the screenshot is always saved to disk; `screenshotFilePath` is returned. By default `outputPath` is the OS temp dir and `name` is \\\"screenshot\\\" (same as content_take-screenshot). Use `screenshotOptions.includeBase64: true` only when the file cannot be read from the returned path (e.g. remote, container).\\n        \",\"params\":[\"direction\",\"timeout\",\"waitUntil\",\"waitForNavigation\",\"waitForTimeoutMs\",\"includeSnapshot\",\"snapshotOptions\",\"includeScreenshot\",\"screenshotOptions\"]},{\"name\":\"navigation_go-to\",\"description\":\"\\nNavigates to the given URL.\\n**NOTE**: The tool either throws an error or returns a main resource response. \\nThe only exceptions are navigation to `about:blank` or navigation to the same URL with a different hash, \\nwhich would succeed and return empty response.\\n\\n**By default** (`includeSnapshot: true`), an ARIA snapshot with refs is taken after navigation and returned in `output` and `refs`; you can use refs (e1, e2, ...) in interaction tools without calling a11y_take-aria-snapshot separately. Use `snapshotOptions` for `interactiveOnly` (default false) and `cursorInteractive` (default false). Set `includeSnapshot: false` to get only url/status/ok.\\n\\nWhen `includeScreenshot: true`, the screenshot is always saved to disk; `screenshotFilePath` is returned. By default `outputPath` is the OS temp dir and `name` is \\\"screenshot\\\" (same as content_take-screenshot). Use `screenshotOptions.includeBase64: true` only when the file cannot be read from the returned path (e.g. remote, container).\\n        \",\"params\":[\"url\",\"timeout\",\"waitUntil\",\"waitForNavigation\",\"waitForTimeoutMs\",\"includeSnapshot\",\"snapshotOptions\",\"includeScreenshot\",\"screenshotOptions\"]},{\"name\":\"navigation_reload\",\"description\":\"\\nReloads the current page.\\nIn case of multiple redirects, the navigation resolves with the response of the last redirect.\\nIf the reload does not produce a response, returns empty response.\\n\\nBy default (includeSnapshot: true), an ARIA snapshot with refs is returned. Use `snapshotOptions` for `interactiveOnly` (default false) and `cursorInteractive` (default false), same as a11y_take-aria-snapshot.\\n\\nWhen `includeScreenshot: true`, the screenshot is saved to disk; `screenshotFilePath` is returned. Default path/name: OS temp dir and \\\"screenshot\\\" (same as content_take-screenshot). Use `screenshotOptions.includeBase64: true` only when the file cannot be read from the path.\\n        \",\"params\":[\"timeout\",\"waitUntil\",\"waitForNavigation\",\"waitForTimeoutMs\",\"includeSnapshot\",\"snapshotOptions\",\"includeScreenshot\",\"screenshotOptions\"]},{\"name\":\"o11y_get-console-messages\",\"description\":\"Retrieves console messages/logs from the browser with filtering options.\",\"params\":[\"type\",\"search\",\"timestamp\",\"sequenceNumber\",\"limit\"]},{\"name\":\"o11y_get-http-requests\",\"description\":\"Retrieves HTTP requests from the browser with filtering options.\",\"params\":[\"resourceType\",\"status\",\"ok\",\"timestamp\",\"sequenceNumber\",\"limit\",\"includeRequestHeaders\",\"includeResponseHeaders\",\"includeResponseBody\"]},{\"name\":\"o11y_get-trace-context\",\"description\":\"Gets the OpenTelemetry trace context (trace id and tracestate) from the live browser page when OTEL is enabled.\",\"params\":[]},{\"name\":\"o11y_get-web-vitals\",\"description\":\"Collects Web Vitals (LCP, INP, CLS, TTFB, FCP) with Google thresholds and recommendations.\\nCall after navigation or user actions; use waitMs for more stable LCP/CLS/INP.\\nSome metrics may be unavailable depending on browser and interactions.\",\"params\":[\"waitMs\",\"includeDebug\"]},{\"name\":\"o11y_new-trace-id\",\"description\":\"Generates new OpenTelemetry compatible trace id and sets it to the current session.\",\"params\":[]},{\"name\":\"o11y_set-trace-context\",\"description\":\"Sets or clears the OpenTelemetry trace context. Empty traceId clears the MCP-pinned trace id (new browser traces get random ids). Empty traceState clears tracestate. Non-empty traceState must be valid W3C tracestate (comma-separated key=value list).\",\"params\":[\"traceId\",\"traceState\"]},{\"name\":\"react_get-component-for-element\",\"description\":\"Finds React component(s) for a DOM element via React Fiber (best-effort). Give selector or (x,y); we resolve the element,\\nfind __reactFiber$ on it or ancestors, then build the component stack from the host fiber that owns that node.\\nFiber is not a public API—results vary by dev/prod build; names can be displayName, wrappers, or minified.\\nwrappersDetected/wrapperFrames help with memo/forwardRef/context. If hostMapping.strategy is ancestor-fallback,\\nuse a more specific selector or deeper node for better accuracy.\",\"params\":[\"selector\",\"x\",\"y\",\"maxStackDepth\",\"includePropsPreview\",\"maxPropsPreviewChars\"]},{\"name\":\"react_get-element-for-component\",\"description\":\"Maps a React component instance to the DOM elements it renders (DOM footprint) by traversing the Fiber graph.\\nPrefer an anchor (anchorSelector or anchorX/anchorY) to target the instance; optionally add a query\\n(componentName, fileNameHint, lineNumber) to search Fiber. With both, we rank candidates and pick the best match near the anchor.\\nReact DevTools hook gives reliable root discovery (getFiberRoots); without it we fall back to DOM scan for __reactFiber$ (best-effort).\\nFor more reliable roots in a persistent browser, install the React Developer Tools Chrome extension.\\nDebug source is best-effort and may be missing in some builds.\",\"params\":[\"anchorSelector\",\"anchorX\",\"anchorY\",\"componentName\",\"matchStrategy\",\"fileNameHint\",\"lineNumber\",\"maxElements\",\"onlyVisible\",\"onlyInViewport\",\"textPreviewMaxLength\",\"maxMatches\"]},{\"name\":\"scenario-add\",\"description\":\"Adds a new scenario. A scenario is a reusable JS script (like execute) that can call tools via callTool().\\nScenarios are stored on disk under the scenarios.json file (project-level by default, or global with scope=\\\"global\\\").\",\"params\":[\"name\",\"description\",\"script\",\"scope\"]},{\"name\":\"scenario-update\",\"description\":\"Updates an existing scenario's description and/or script.\",\"params\":[\"name\",\"description\",\"script\",\"scope\"]},{\"name\":\"scenario-delete\",\"description\":\"Deletes a scenario by name.\",\"params\":[\"name\",\"scope\"]},{\"name\":\"scenario-list\",\"description\":\"Lists all available scenarios. When scope is omitted, returns scenarios from both project and global scopes (project overrides global for same name).\",\"params\":[\"scope\"]},{\"name\":\"scenario-search\",\"description\":\"Searches scenarios by query across both project and global scopes.\\nUses configurable search strategy (SEARCH_STRATEGY or SCENARIO_SEARCH_STRATEGY env var).\\nReturns matching scenarios ranked by relevance.\",\"params\":[\"query\",\"limit\"]},{\"name\":\"stub_clear\",\"description\":\"Clears stubs installed.\\n\\n- If stubId is provided, clears only that stub.\\n- If stubId is omitted, clears all stubs for the current session/context.\",\"params\":[\"stubId\"]},{\"name\":\"stub_intercept-http-request\",\"description\":\"Installs a request interceptor stub that can modify outgoing requests before they are sent.\\n\\nUse cases:\\n- A/B testing / feature flags (inject headers)\\n- Security testing (inject malformed headers / payload)\\n- Edge cases (special characters, large payload)\\n- Auth simulation (add API keys / tokens in headers)\\n\\nNotes:\\n- pattern is a glob matched against the full request URL (picomatch).\\n- This modifies requests; it does not change responses.\\n- times limits how many times the interceptor applies (-1 means infinite).\",\"params\":[\"pattern\",\"modifications\",\"delayMs\",\"times\"]},{\"name\":\"stub_list\",\"description\":\"Lists currently installed stubs for the active browser context/session.\\nUseful to debug why certain calls are being mocked/intercepted.\",\"params\":[]},{\"name\":\"stub_mock-http-response\",\"description\":\"Installs a response stub for matching requests using glob patterns (picomatch).\\n\\nUse cases:\\n- Offline testing (return 200 with local JSON)\\n- Error scenarios (force 500/404 or abort with timedout)\\n- Edge cases (empty data / huge payload / special characters)\\n- Flaky API testing (chance < 1.0)\\n- Performance testing (delayMs)\\n\\nNotes:\\n- pattern is a glob matched against the full request URL.\\n- stubs are evaluated in insertion order; first match wins.\\n- times limits how many times the stub applies (-1 means infinite).\",\"params\":[\"pattern\",\"response\",\"delayMs\",\"times\",\"chance\"]},{\"name\":\"sync_wait-for-network-idle\",\"description\":\"Waits until the page is network-idle: in-flight requests <= maxConnections for at least idleTimeMs (server-side tracking, no page globals).\\nUse before SPAs, screenshots, or AX snapshots for stable results. With long-polling, increase maxConnections or use shorter idleTimeMs.\",\"params\":[\"timeoutMs\",\"idleTimeMs\",\"maxConnections\",\"pollIntervalMs\"]},{\"name\":\"execute\",\"description\":\"Batch-execute multiple tool calls in a single request via custom JavaScript. Reduces round-trips and token usage.\\n\\n**IMPORTANT** \\n- The code is already run inside an async function. Pass only the body (statements). \\n  Do NOT wrap in `async function() { ... }` or `async () => { ... }` — that causes a syntax error. \\n  Write `await callTool(...); return x;` directly.\\n\\n**IMPORTANT:** \\n- `page` (Playwright Page) is available in the VM — use it for navigation or `page.evaluate()`. \\n- Prefer interaction tools with refs (e1, e2 from a11y_take-aria-snapshot); use raw Playwright only as last resort.\\n- `document`/`window` are not in the VM — use `page.evaluate(() => { ... })` to run code in the browser.\\n- Use `waitForNavigation: true` on interaction_click when the click navigates. \\n- After navigation, do not continue with refs from the previous page — take fresh refs with a11y_take-aria-snapshot first.\\n\\nBindings:\\n- await callTool(name, input, returnOutput?): async — always use with await. Returns the tool output for in-code use.\\n  returnOutput=true also includes it in the response toolOutputs array; false (default) omits it.\\n  Throws on failure — execution stops at the first error; partial toolOutputs/logs are still returned.\\n  On failure, failedTool in the response identifies which tool caused the error.\\n  Max 50 callTool invocations per execution.\\n- console.log/warn/error: captured in the response logs array.\\n- sleep(ms): async delay.\\n\\nBuilt-ins: Math, JSON, Date, RegExp, Number, String, Boolean, Array, Object, Promise, Map, Set, WeakMap, WeakSet, \\n           Symbol, Proxy, Reflect, URL, URLSearchParams, TextEncoder/Decoder, structuredClone, \\n           crypto.randomUUID(), AbortController, setTimeout/clearTimeout.\\nNOT available: require, import, process, fs, Buffer, fetch.\\n\\n\\n**Example** — fill form, submit (with navigation wait), then snapshot and screenshot:\\n  await callTool('interaction_fill', { selector: 'e3', value: 'user@test.com' });\\n  await callTool('interaction_fill', { selector: 'e5', value: 'secret123' });\\n  await callTool('interaction_click', { selector: 'e7', waitForNavigation: true });\\n  // Or with page.locator: await page.locator('button').click();\\n  // Or with page.evaluate: await page.evaluate(() => document.querySelector('button').click());\\n  await callTool('a11y_take-aria-snapshot', {}, true);\\n  await callTool('content_take-screenshot', {}, true);\",\"params\":[\"code\",\"timeoutMs\"]},{\"name\":\"scenario-run\",\"description\":\"Runs a saved scenario by name. Looks up the scenario in project scope first, then global.\\nThe scenario's JS script runs in the same sandbox as execute: callTool(), console, sleep are available.\\nScenarios can compose other scenarios via callTool('scenario-run', { name: '...' }).\\nMax recursion depth: 5.\",\"params\":[\"name\",\"timeoutMs\"]}],\"toolsHash\":\"8b88a3b389b3466bb23cc170430d0f3832adcd266e52cf92178b5a934abbb001\",\"wrote\":[\"/tmp/.browser-devtools-mcp/config.json\"],\"callsAt\":\"2026-11-16T11:27:46.543Z\",\"calls\":[{\"tool\":\"content_get-as-html\",\"ok\":false,\"ms\":13,\"bytes\":0,\"error\":\"tool reported an error: Error: browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium_headless_shell-1255/chrome-headless-shell-linux64/chrome-headless-shell\\n╔═════════════════════════════════════\"},{\"tool\":\"content_get-as-text\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium_headless_shell-1255/chrome-headless-shell-linux64/chrome-headless-shell\\n╔═════════════════════════════════════\"},{\"tool\":\"debug_status\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium_headless_shell-1255/chrome-headless-shell-linux64/chrome-headless-shell\\n╔═════════════════════════════════════\"},{\"tool\":\"o11y_get-trace-context\",\"ok\":false,\"ms\":0,\"bytes\":0,\"error\":\"tool reported an error: Error: browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium_headless_shell-1255/chrome-headless-shell-linux64/chrome-headless-shell\\n╔═════════════════════════════════════\"},{\"tool\":\"o11y_get-web-vitals\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium_headless_shell-1255/chrome-headless-shell-linux64/chrome-headless-shell\\n╔═════════════════════════════════════\"}],\"host\":{\"commit\":\"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c\",\"run\":\"https://github.com/itsHaddad/bragproof/actions/runs/43857070216\"},\"network\":{\"names\":[\"registry.npmjs.org\"],\"conns\":[],\"callNames\":[],\"callConns\":[]}}","token":"eyJhbGciOiJSUzI1NiIsImtpZCI6IjM4ODI2YjE3LTZhMzAtNWY5Yi1iMTY5LThiZWI4MjAyZjcyMyIsInR5cCI6IkpXVCIsIng1dCI6InlrTmFZNHFNX3RhNGsyVGdaT0NFWUxrY1lsQSJ9.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.esZZDmJaxdmKw3Sl9ySKH4rklJ-jj6JfvKgsjub1XwmWvOHizGyZ6CeWgaxCX1jqftITvxAoGZGXn0-IE4QHkH89s6miyYM6YC6yb-bPq8BqfO7NrplnAKqNyl8aGs37dpv3JKgvkUgn3zZrZectpssNwIrz2ZgzApTKStHLA6c4BXzKpWG4NVTjgc8kfLMWMSNYie89UNeLVCp-V6uDqOJeHr7pLy6DiYOdan0HvDipFzZ3T4gz0Ib7nzHJZDZBh5akL82u4TSt7UsqCNi-WIpmY8F5KKUglTaj5Vluzpvk2w8TSZDXtaC_Xa52znR59UI_2x0fNMLrnGzln6NhWA"}