MCP-Server

Aginx Browser

net.aginx/aginxbrowser
Entwicklertools Öffentlich und erreichbar MCP 2025-11-25

Was dieses MCP kann

Provides stateful browser automation for web search, page fetching, clicking, typing, downloads, logins, session recording, and deterministic rendering.

account_delete
Delete a named login identity: stored record AND live jar. Cookie values are credentials — delete means gone. Sessions currently running as the account keep their in-process jar handle, but nothing writes back. Returns {deleted: name}, or an error naming the account if it does not exist.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'The account to delete: stored record AND live jar.'}}}
account_list
List named login identities (the multi-account layer) with metadata only: name, cookie domains, cookie count, updated_at, the last account_verify verdict, and the identity's persona User-Agent (each account is one stable device: its own UA and hardware fingerprint, drawn once and reused). Cookie values are credentials and never leave the server. Use to see which identities exist before session_create {account} picks one.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {}}
account_login
Open a site's login page AS a named account and close the login loop. Creates the session as the account (private jar, device persona), navigates to `url`, and reports which generic login gates the page shows — needs: password | sms | qr | slider (QR scan like xiaohongshu, SMS code, password form, slider/captcha) — plus a session_verdict classification and, when a human step is needed, the session_id and a /live handoff so a person can finish it in the live view (the engine detects and describes; it never fills credentials or solves challenges). With `predicate` and no human gates detected, waits for the automatic bounce, then teaches + stamps the account's verify spec — later account_verify calls re-check it bare. Cookies write back after every action, so a login finished in /live is already persisted. status is "logged_in" (verify stamped), "waiting" (drive session_wait/session_input on session_id, or re-call account_login after the human finishes — the account's shared jar already holds it), or "opened" (no predicate given).
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name', 'url'], 'properties': {'url': {'type': 'string', 'description': 'The login page URL to open as this account.'}, 'name': {'type': 'string', 'description': 'The account to log in as (created implicitly on first use; 1-64\nchars of [a-zA-Z0-9_-]).'}, 'predicate': {'type': ['string', 'null'], 'default': None, 'description': "A JS expression truthy on the page the site lands on AFTER login,\ne.g. `!!document.querySelector('.user-nick')`. With it and no human\nstep detected, the call waits for the automatic login bounce and\nstamps the account's verify spec on success. Without it, the call\njust opens the page and reports what kind of login it sees."}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through the engine proxy. Seeds a fresh account; an account\nwith an existing record reuses its recorded egress.'}, 'timeout_ms': {'type': 'integer', 'format': 'uint64', 'default': 60000, 'minimum': 0, 'description': 'Wait budget in ms for the automatic-login bounce (default 60000,\nclamped 1000..120000). Never spent while a human step\n(QR/SMS/password/slider) is outstanding â\x80\x94 those return immediately\nwith a session handoff.'}}}
account_verify
Check whether a named account is still logged in. Teach-once: the first call passes url + predicate (a JS expression truthy on a logged-in page, e.g. !!document.querySelector('.user-nick')); the spec is remembered and later calls can be bare. Runs in a scratch session AS the account (private jar), so the probe doubles as a cookie refresh. Returns {name, logged_in, url, checked_at}.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name'], 'properties': {'url': {'type': ['string', 'null'], 'default': None, 'description': 'Teach-once: the page that shows login state (its login wall if the\naccount is logged out). Remembered after the first call.'}, 'name': {'type': 'string', 'description': 'The account to check.'}, 'predicate': {'type': ['string', 'null'], 'default': None, 'description': "Teach-once: a JS expression that is truthy when logged in, e.g.\n`!!document.querySelector('.user-nick')`. Remembered after the first\ncall â\x80\x94 later calls can pass neither and rerun the spec."}}}
cache
Query the LOCAL CACHE of every page this server has fetched and every search it has run. Check here BEFORE re-fetching or re-searching — a hit is instant and free while a fresh fetch costs 5-60s. Use query for full-text search (works for Chinese substrings and English words), get to pull a page's full cached content, stats for counts, clear to delete rows.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'all': {'type': 'boolean', 'default': False, 'description': 'With clear: delete everything cached for this caller'}, 'get': {'type': ['string', 'null'], 'default': None, 'description': 'Return the FULL cached content of this exact URL instead of listing hits'}, 'url': {'type': ['string', 'null'], 'default': None, 'description': 'Only rows whose URL contains this substring'}, 'kind': {'type': ['string', 'null'], 'default': None, 'description': 'Which rows to search: "auto" (default, pages + searches), "pages", or "searches"'}, 'clear': {'type': 'boolean', 'default': False, 'description': 'Delete matching rows instead of returning them (requires url, since_hours, or all)'}, 'limit': {'type': 'integer', 'format': 'uint', 'default': 10, 'minimum': 0, 'description': 'Maximum rows returned (default: 10, max 100)'}, 'query': {'type': ['string', 'null'], 'default': None, 'description': 'Full-text search over cached page contents, titles, URLs and past search queries. Omit to list the latest rows.'}, 'stats': {'type': 'boolean', 'default': False, 'description': 'Return row counts and database size instead of rows'}, 'since_hours': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Only rows stored within the last N hours'}}}
click
Click an element on a one-off page: loads `url` in a fresh browser context (stateless — no cookies unless passed, no shared state with other calls), waits `wait_secs` after load before clicking, then fires a DOM click on the first CSS-selector match. The click may trigger navigation (link, form submit) — the response `url` and `text_after` are read after that navigation lands. Returns `clicked:false` when the selector matches nothing. For multi-step interaction on a shared page use session_click instead.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url', 'selector'], 'properties': {'url': {'type': 'string', 'description': 'The URL to load'}, 'selector': {'type': 'string', 'description': 'CSS selector of element to click'}, 'wait_secs': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Seconds to wait for the page to settle after load, before clicking'}}}
download
Download a file over HTTP(S) with streaming to disk (no memory buffering), SHA-256 integrity hash, and optional resume of interrupted transfers. Filename resolution: explicit param → Content-Disposition → URL tail. Use for binaries, archives, datasets, documents - anything where the agent wants the FILE saved, not its text content read.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL of the file to download (http/https)'}, 'resume': {'type': 'boolean', 'default': False, 'description': 'Resume an interrupted download when a local partial file exists'}, 'cookies': {'type': 'array', 'items': {'type': 'string'}, 'default': [], 'description': 'Cookies to send with the request: `"name=value"` strings or\nCDP-style objects `{"name","value","domain",...}` for gated downloads'}, 'filename': {'type': ['string', 'null'], 'default': None, 'description': 'Explicit output filename. When omitted: Content-Disposition â\x86\x92 URL tail â\x86\x92 "download"'}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through proxy (default: false; auto-enabled for known blocked domains)'}}}
eval
Execute JavaScript on a one-off page: loads `url` in a fresh browser context, optionally waits `wait_secs` for the page to settle, evaluates `script` (async/Promise supported) and returns `{url, result}`. Script-driven navigation (location.href, form submit) is drained and reflected in the returned `url`. Stateless — no cookies or page state shared with other calls; when the script needs prior page state or a login, use session_eval.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url', 'script'], 'properties': {'url': {'type': 'string', 'description': 'The URL to load'}, 'script': {'type': 'string', 'description': 'JavaScript code to execute (supports async/Promise)'}, 'wait_secs': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Seconds to wait before executing'}}}
fetch
Fetch a webpage and return clean markdown/html/text. Use whenever the agent needs to READ any web page - blogs, docs, articles, JS-rendered SPAs, Cloudflare-protected sites. Static pages are served over plain HTTP (~100ms tier:"http"); pages that need JS get the full browser (tier:"browser"). render_tier selects auto (default) / http (pure HTTP, refuses the upgrade) / browser (always the JS browser).
Nur Lesen
Eingabeschema
{'type': 'object', '$defs': {'RenderTier': {'oneOf': [{'type': 'string', 'const': 'auto', 'description': 'HTTP-direct first, fall back to diting browser. (default)'}, {'type': 'string', 'const': 'http', 'description': 'Pure HTTP, no V8/JS. Fastest; misses JS-rendered content.'}, {'type': 'string', 'const': 'browser', 'description': 'Always use the diting browser (current behaviour pre-tiering).\nWire name is "browser". "obscura" is still accepted and not advertised.'}], 'description': 'Tiered rendering strategy selector.'}, 'JsExtractParams': {'type': 'object', 'required': ['expression'], 'properties': {'expression': {'type': 'string', 'description': 'JavaScript expression to evaluate (e.g. "window.__INITIAL_STATE__")'}, 'timeout_ms': {'type': 'integer', 'format': 'uint64', 'default': 5000, 'minimum': 0, 'description': 'Timeout in milliseconds (default: 5000)'}}}}, '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The URL to fetch'}, 'format': {'type': 'string', 'default': 'markdown', 'description': 'Output format: "markdown", "html", or "text" (default: markdown)'}, 'sanitize': {'type': 'boolean', 'default': True, 'description': 'Strip prompt-injection payloads from the text output (default true):\nzero-width/steganographic characters, instruction-shaped lines\n("ignore previous instructions", chat markup tokens, CJK variants),\nand text hidden via opacity:0 / tiny fonts. A `sanitize_report`\nfield counts what was removed â\x80\x94 stripping is observable, never\nsilent. Set false for raw output.'}, 'selector': {'type': ['string', 'null'], 'default': None, 'description': 'CSS selector to extract specific content'}, 'max_chars': {'type': 'integer', 'format': 'uint', 'default': 50000, 'minimum': 0, 'description': 'Maximum characters to return (default: 50000)'}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through proxy (for blocked foreign sites)'}, 'wait_secs': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Seconds to wait for JS rendering'}, 'js_extract': {'anyOf': [{'$ref': '#/$defs/JsExtractParams'}, {'type': 'null'}], 'default': None, 'description': 'JS expression to extract from the page after rendering'}, 'capture_xhr': {'type': ['array', 'null'], 'items': {'type': 'string'}, 'default': None, 'description': 'Capture script-initiated API responses: a list of URL substrings\n(e.g. ["/api/"]) whose matching fetch/XHR bodies come back in an\n`xhr` array; an empty list captures every XHR/Fetch. Forces browser\nrendering (script-initiated requests only exist after JS runs).'}, 'render_tier': {'$ref': '#/$defs/RenderTier', 'default': 'auto', 'description': 'Rendering strategy: "auto" (default), "http", or "browser"'}, 'tls_fingerprint': {'type': ['string', 'null'], 'default': None, 'description': 'TLS fingerprint override (stealth mode only): "chrome145", "firefox133", etc.'}, 'auto_bypass_challenge': {'type': 'boolean', 'default': True, 'description': 'Auto-detect and bypass Cloudflare Turnstile challenges (default: true)'}}}
flow_install
Install a third-party flow from DupHub into the server's workflow directory, making it runnable by name via flow_run. Pulls the template's manifest, verifies every file's sha256 against it (a package that fails anywhere is not installed), requires a valid flow.json with a steps array, and lands atomically under workflow/<name>/ — replacing any previous install, overriding a same-named built-in. The receipt lists files, total bytes, step count, and how many steps carry scripts (eval_steps) — third-party scripts run with this engine's privileges in session pages, so review before running. Source remote is env-configured (AGINXBROWSER_DUPHUB_URL), never a parameter.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Workflow name â\x80\x94 the DupHub template to pull and the directory it\nlands in (workflow/<name>/). Lowercase/digits/dashes.'}}}
flow_run
Run a flow — a recorded, editable JSON browser-session script — deterministically, with zero model tokens. Steps are {op, args, expect?, save?}: ops cover navigate/click/click_xy/input/scroll/eval/wait/screenshot/state/cookies; {{var}} placeholders in args are filled from vars; expect asserts (url_contains | selector | text_contains | eval_truthy) abort with evidence on failure; save collects a step's output into the receipt. Source the flow inline via "flow", or by "name" from the server's workflow/<name>/flow.json (unknown name → error lists installed workflows). Pass session_id to reuse a live session (e.g. from import_curl) so login state and flows compose. The receipt carries status ok/failed, saved outputs, the session_id (kept alive), and on failure the failing step, reason and a diagnostic screenshot — fix the flow or take the session over from there.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'flow': {'default': None, 'description': 'Inline flow document: {create?, vars?, steps:[{op, args, expect?, save?}]}'}, 'name': {'type': ['string', 'null'], 'default': None, 'description': 'Or run a server-side workflow/<name>/flow.json asset. An unknown name\nerrors back with the list of installed workflows â\x80\x94 that error is the\ndiscovery call.'}, 'vars': {'default': None, 'description': "Values for {{placeholders}} in step args; wins over the flow's own\nvars defaults."}, 'max_steps': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': "Override the run's step-execution budget (branch loops re-run steps,\nso every revisit counts). Default 1000, clamped 1..=100000. A flow\ndocument may also declare its own max_steps; this wins."}, 'session_id': {'type': ['string', 'null'], 'default': None, 'description': "Reuse a live session (e.g. from import_curl) instead of creating a\nfresh one â\x80\x94 that's how login state and flows compose."}}}
flow_search
List flow packages installable from the hub (env-configured AGINXBROWSER_DUPHUB_URL, default the public DupHub) — flow discovery: flow_install takes a name, this is how you learn the names. Each entry carries name/description/version/downloads; feed the name to flow_install. Queries the market's kind=agx-flow filter (flows are templates whose package root carries flow.json) and re-filters client-side, so clones never surface as flows. A hub predating the kind protocol reports kind_filter unsupported instead of guessing.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'query': {'type': 'string', 'default': '', 'description': "Optional substring to narrow the listing (the hub's q filter over\nname/description). Empty lists everything installable."}}}
import_curl
Import login state from a real browser in one paste. The human logs into a site in their own Chrome (solving the CAPTCHA/SMS once), opens DevTools → Network, right-clicks any authenticated request → "Copy as cURL", and passes the command here. Returns a live session_id already carrying that site's cookies and sitting on the copied request's URL — the agent continues from where the human left off, no password or second login needed. Works with bash, PowerShell and cmd copy flavors.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['curl'], 'properties': {'curl': {'type': 'string', 'description': 'A "Copy as cURL" command pasted from Chrome DevTools (Network panel â\x86\x92\nright-click any authenticated request). bash, PowerShell and cmd\nflavors all parse; the cookie set is injected and the session\nnavigates to the copied request\'s URL.'}, 'account': {'type': ['string', 'null'], 'default': None, 'description': "Attach the session to a named account: the imported login lands in\nthe account's private jar and is written back under its name after\nevery action â\x80\x94 one import per identity, no clobbering."}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': "Route the session's traffic through the engine proxy."}}}
render_markdown
Render a markdown document into a deterministic, self-contained HTML artifact - the document layer, so the agent never writes HTML by hand. Prose rides a plain offline shell (no fonts, no scripts); archify fenced code blocks carry typed zero-coordinate diagram JSON (sequence, workflow, architecture, dataflow, lifecycle families) and render to inline SVG via the layout engine. Same input, same bytes: the receipt carries the sha256 so determinism is verifiable. theme picks light (default) or dark; preset picks the palette family — classic (default), signal-flow, blueprint, editorial — orthogonal to theme; colors bake at generation time (presentation attributes, not CSS variables), and the receipt records both preset and theme. quality picks the composition audit profile — standard (default) or showcase, the delivery gate: the receipt's diagrams[].composition grades route crossings, ambiguous corridors, label clearance (2px standard / 4px showcase), route rhythm, and node text projected to the 930px reader width; the audit never changes the artifact bytes. Mermaid sources are the agent's job to translate, not the engine's: flowchart/graph → workflow (lanes + columns), sequenceDiagram → sequence, stateDiagram-v2 → lifecycle (bands), erDiagram/class → architecture (grid + boundaries) — read the topology and emit the matching zero-coordinate archify JSON; the engine accepts only archify JSON. A broken diagram degrades to a visible code block and lands in receipt.diagnostics; an authored route preset that cannot be honored is self-repaired to a verified semantic substitute and disclosed in receipt diagrams[].repairs - the document still renders. A fence may also carry views: [{id,label,nodes,note?}] (node ids of the active family), emitted as guided-view tabs above the diagram plus an inlined viewer script - clicking a tab lights the member nodes and the routes between them (subgraph), clicking a node lights it with its direct neighbors (ego graph), everything else dims; a view's optional note shows as a caption while it is active (the story layer). window.agxViewer in a session drives and reads the same state programmatically: {focus,view,state} as before, plus route(i,from,to) which returns and lights the shortest authored directed path between two nodes (null when unreachable, state untouched), and reach(i,id,down|up) which returns and lights the authored downstream/upstream closure ({nodes,links}); both dim the rest of the diagram. diagrams[].views in the receipt lists the tabs. motion: true bakes an entrance choreography into the artifact: pure-declarative CSS animation with zero scripts - headings split into per-glyph (CJK) / per-word (latin) spans that rise in with expo easing, prose blocks stagger up an nth-child delay ladder, diagram figures grow in with a back ease (GSAP's easing math as public cubic-bezier equivalents, nothing embedded); the diagrams themselves play a flow story on the same clock - nodes land beat by beat, solid edges draw in (dash-offset), dashed returns fade, sequence messages arrive as sent - with a timed caption strip under each figure as the subtitles, which becomes a static transcript under prefers-reduced-motion; the file itself animates in any browser and the receipt records motion plus diagrams[].story (beat times and captions - the hook for muxing voice later). With session_id the artifact is also loaded into that session (local, free) and the reply carries viewport acceptance: scroll extents measured in the live session and graded fits/tall/wide/oversized, telling the agent how to read the page back. Diagram vocabulary adapted from archify (MIT).
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['markdown'], 'properties': {'theme': {'type': ['string', 'null'], 'description': 'Color theme: "light" (default) or "dark" â\x80\x94 the shell background/\nforeground and every SVG palette slot swap together; the receipt\nrecords which theme produced the bytes'}, 'motion': {'type': ['boolean', 'null'], 'description': 'Bake the entrance choreography into the artifact (default false):\npure-declarative CSS animation â\x80\x94 headings split into per-glyph/per-\nword spans that rise in with expo easing, prose blocks stagger up a\nnth-child delay ladder, and diagram figures grow in with a back\nease (GSAP\'s easing math as public cubic-bezier equivalents). The\ndiagrams animate too, on one story clock: nodes pop in one beat at\na time, solid edges draw themselves (dash-offset drain), dashed\nreturns fade, sequence messages land as they are "sent", and a\ntimed caption strip under each figure subtitles the beats â\x80\x94 under\nprefers-reduced-motion the strip becomes a static transcript.\nZero scripts: the file itself animates in any browser, subtitles\nand all; the receipt records motion (plus diagrams[].story with\nthe beat times, the hook for muxing voice later) so a cached\nartifact is never mistaken for the static one'}, 'preset': {'type': ['string', 'null'], 'description': 'Visual preset: "classic" (default), "signal-flow", "blueprint", or\n"editorial" â\x80\x94 a palette family orthogonal to theme (each preset\nexists in both light and dark). The receipt records preset and\ntheme separately'}, 'quality': {'type': ['string', 'null'], 'description': 'Quality profile for the composition audit: "standard" (default) or\n"showcase" â\x80\x94 the delivery gate. The audit grades route crossings,\ncorridors, label clearance, rhythm, and projected text size in the\nreceipt (diagrams[].composition); it never changes the artifact\nbytes, only how findings are severity-rated'}, 'markdown': {'type': 'string', 'description': 'Full markdown document. Prose rides a plain offline shell; archify\nfenced code blocks carry typed zero-coordinate diagram JSON and\nrender to inline SVG.'}, 'session_id': {'type': ['string', 'null'], 'description': 'Optional session ID: also load the rendered HTML into that live\nsession (local and free) so session_screenshot / session_state can\nverify the artifact'}}}
render_pdf
Cut a rendered page into pages and package as PDF, PNGs, PPTX or DOCX. Print mode (no selector) paginates the document into fixed-height pages (default 794x1123, A4 @96dpi), breaking at top-level block boundaries — no half-cut text where a break can land on a block edge. Slides mode (selector set) makes one page per match, sized to that element — generate an HTML deck with one .slide per page and each becomes a deck page. format "pdf" (default) returns base64 image-based PDF; "png" returns one base64 PNG per page in pages_base64; "pptx" returns a base64 PPTX (one slide per page, deck-sized to the largest page); "docx" returns a base64 DOCX (one page-sized section per page, each section keeps its own height). Returns page count and packaging.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Page URL to cut into pages.'}, 'width': {'type': 'integer', 'format': 'uint32', 'default': 794, 'minimum': 0, 'description': 'Page width in CSS pixels. Default 794 (A4 @96dpi).'}, 'format': {'type': 'string', 'default': 'pdf', 'description': 'Output format: "pdf" (default), "png" (one base64 PNG per page),\n"pptx" (one slide per page, image-based), "pptx-native" (editable:\nelement-level DrawingML â\x80\x94 real text runs, gradient shapes, image\nparts; requires `selector`), or "docx" (one page-sized section per\npage).'}, 'height': {'type': 'integer', 'format': 'uint32', 'default': 1123, 'minimum': 0, 'description': 'Page height in CSS pixels â\x80\x94 print pagination only. Default 1123.'}, 'selector': {'type': ['string', 'null'], 'default': None, 'description': 'CSS selector; present â\x86\x92 slides mode (one page per match, sized to the\nelement). Absent â\x86\x92 print mode (fixed-height pages at block boundaries).'}, 'max_pages': {'type': 'integer', 'format': 'uint', 'default': 50, 'minimum': 0, 'description': 'Safety cap on emitted pages. Default 50.'}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through proxy (for blocked foreign sites)'}, 'jpeg_quality': {'type': 'integer', 'format': 'uint8', 'default': 90, 'maximum': 255, 'minimum': 0, 'description': 'JPEG quality for PDF page embedding (1-100). Default 90.'}, 'tls_fingerprint': {'type': ['string', 'null'], 'default': None, 'description': 'TLS fingerprint override (stealth mode only)'}}}
render_video
Render a page's animation timelines to an MP4 video. The page's scripts must expose `window.__timelines` — objects with `duration()` and `pause(t)` (a paused gsap.timeline registered there works as-is). Each frame seeks every timeline to t=i/fps and paints the viewport, so the output is deterministic — no wall clock in the pixel values. Audio: `narration[]` places TTS/voice clips at start times (mixed into one AAC track), `audio` adds looped background music, and `subtitles_srt` muxes an SRT as a soft mov_text track and (by default, `burn_subtitles: false` to opt out) burns the same cues into the frame pixels — QuickTime, WeChat and most social embeds ignore the soft track. Requires ffmpeg on the server. Returns base64 MP4 (H.264, yuv420p) plus frame count and durations.
Eingabeschema
{'type': 'object', '$defs': {'RenderVideoAudio': {'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL of the music file. mp3/wav/ogg/m4a â\x80\x94 probed by content.'}, 'volume': {'type': 'number', 'format': 'float', 'default': 1.0, 'description': 'Linear multiplier 0..=2; 1 = as authored. Default 1.'}, 'loop_audio': {'type': 'boolean', 'default': True, 'description': 'Loop to cover the whole video. Default true.'}, 'fade_out_secs': {'type': 'number', 'format': 'float', 'default': 0.0, 'description': 'Fade out over the final N seconds. Default 0 (none).'}}, 'description': 'render_video `audio`: background music track â\x80\x94 fetched, looped to cover\nthe video, volume-scaled, optionally faded out at the end.'}, 'RenderNarrationClip': {'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL of the voice clip (any TTS output; mp3/wav/ogg/m4a).'}, 'volume': {'type': 'number', 'format': 'float', 'default': 1.0, 'description': 'Linear multiplier 0..=2. Default 1.'}, 'start_secs': {'type': 'number', 'format': 'double', 'default': 0.0, 'description': 'Seconds from video t=0 where this line starts. Default 0.'}}, 'description': 'render_video `narration[]`: one voiceover clip placed at a start time â\x80\x94\ngenerate with any TTS, hand us the URL; all clips mix into one AAC track.'}}, '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url'], 'properties': {'fps': {'type': 'number', 'format': 'double', 'default': 24.0, 'description': 'Frames per second. Default 24.'}, 'url': {'type': 'string', 'description': 'Page URL whose scripts register timelines in `window.__timelines`\n(GSAP-style objects with `duration()` + `pause(t)`).'}, 'audio': {'anyOf': [{'$ref': '#/$defs/RenderVideoAudio'}, {'type': 'null'}], 'default': None, 'description': 'Background music: looped to cover the video, volume-scaled, faded\nout at the tail.'}, 'width': {'type': 'integer', 'format': 'uint32', 'default': 1280, 'minimum': 0, 'description': 'Viewport width in CSS pixels (floored to even â\x80\x94 yuv420p). Default 1280.'}, 'height': {'type': 'integer', 'format': 'uint32', 'default': 720, 'minimum': 0, 'description': 'Viewport height in CSS pixels. Default 720.'}, 'narration': {'type': 'array', 'items': {'$ref': '#/$defs/RenderNarrationClip'}, 'default': [], 'description': 'Voiceover clips, each starting at its own time (any TTS output;\nmixed into one AAC track).'}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through proxy (for blocked foreign sites)'}, 'subtitles_srt': {'type': ['string', 'null'], 'default': None, 'description': 'Inline SRT subtitles muxed as a soft (toggleable) mov_text track.'}, 'burn_subtitles': {'type': ['boolean', 'null'], 'default': None, 'description': 'Burn the cues into the frame pixels too (hardsub) â\x80\x94 on by default\nwhen `subtitles_srt` is present; QuickTime, WeChat and most social\nembeds ignore the soft mov_text track. `false` keeps the soft track\nonly.'}, 'hold_tail_secs': {'type': 'number', 'format': 'double', 'default': 0.5, 'description': 'Freeze the final timeline state for this many extra seconds. Default 0.5.'}, 'tls_fingerprint': {'type': ['string', 'null'], 'default': None, 'description': 'TLS fingerprint override (stealth mode only)'}, 'max_duration_secs': {'type': 'number', 'format': 'double', 'default': 120.0, 'description': 'Safety cap on timeline + hold tail, seconds. Default 120.'}, 'wait_timelines_ms': {'type': 'integer', 'format': 'uint64', 'default': 10000, 'minimum': 0, 'description': 'How long to wait for `window.__timelines` to appear, ms. Default 10000.'}, 'subtitles_language': {'type': ['string', 'null'], 'default': None, 'description': 'ISO language tag for the subtitle track, e.g. "eng" / "zh".'}}}
search
Search the web across Baidu/Bing/Sogou/WeChat/Google (aggregated + deduped) and optionally fetch the top results' full content. Use when the agent needs to FIND information online - replaces a search API. Supports image search returning direct image URLs. Optional engines: ["baidu"]-style filter by engine name (invalid names error with the valid list; /doctor lists them with live health). Optional time_range day/week/month/year for news freshness (engines without dated results ignore it). Response carries engine_errors explaining any engine that contributed nothing (CAPTCHA suspension, transient failure).
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['q'], 'properties': {'q': {'type': 'string', 'description': 'Search query'}, 'engines': {'type': 'array', 'items': {'type': 'string'}, 'default': [], 'description': 'Restrict to these engine names (e.g. ["baidu"], ["sogou_wechat"]).\nEmpty = all engines serving `categories`. Invalid names return an\nerror listing the valid ones.'}, 'fetch_top': {'type': 'integer', 'format': 'uint', 'default': 0, 'minimum': 0, 'description': 'Fetch content for top N results'}, 'categories': {'type': 'string', 'default': 'general', 'description': 'Search categories (default: general)'}, 'time_range': {'type': ['string', 'null'], 'default': None, 'description': 'Freshness window: "day" | "week" | "month" | "year". Honored by\nengines with dated results (e.g. bing_news filters by pubDate);\nothers ignore it.'}, 'max_results': {'type': 'integer', 'format': 'uint', 'default': 10, 'minimum': 0, 'description': 'Maximum number of results (default: 10)'}, 'max_chars_per': {'type': 'integer', 'format': 'uint', 'default': 4000, 'minimum': 0, 'description': 'Max characters per result content'}}}
session_challenges
One-call risk-control report: did this session hit an anti-bot wall? Taobao/tmall's x5 risk control answers 200 like a normal response — either a redirect onto a punish page (_____tmd_____/punish, punish.taobao.com) or an MTop API body carrying FAIL_SYS_USER_VALIDATE / RGV587 / x5secdata. Returns {total, events:[{url,method,status,kind,via}]} where via says whether the wall was navigated into ("url") or swallowed by an API response ("body"). When there are hits, the response also carries the account name (which identity got walled) and a `handoff` instruction: the engine detects and surfaces but does not auto-bypass — a human opens the live view (/live?session=<id> on the engine's HTTP port), solves the challenge in this session, and the retry rides the cookie that solving sets. Detection only; no automated solving or bypass.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_click
Click an interactive element by its index (from session_state output) inside a live browser session: scrolls it into view and fires a DOM click on the session's current page. Before clicking it re-verifies the element in the same frame — if the page changed since session_state (element detached, disabled, hidden, or covered by an overlay), it returns `clicked:false` with a `reason` ("detached"/"disabled"/"not_visible"/"covered_by") and, when covered, a `covered_by` description of the element that would eat the click — never a silent no-op. A submit click may navigate the session — the returned `url`/`text_after` reflect the page after the action, and session state (cookies, localStorage, globals) persists for follow-up calls. Indexes come from the most recent session_state; re-list after navigation.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'index'], 'properties': {'index': {'type': 'integer', 'format': 'uint', 'minimum': 0, 'description': 'Element index (from /state output)'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_click_xy
Click at viewport coordinates (CSS pixels) via real mouse events — pointerdown/mousedown, pointerup/mouseup, then click on whatever element is hit there. For canvas/map surfaces with no DOM element to index. click_count 2 adds dblclick.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'x', 'y'], 'properties': {'x': {'type': 'number', 'format': 'double', 'description': 'Viewport X coordinate in CSS pixels'}, 'y': {'type': 'number', 'format': 'double', 'description': 'Viewport Y coordinate in CSS pixels'}, 'button': {'type': ['string', 'null'], 'default': None, 'description': 'Mouse button: "left" (default), "right", "middle"'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'click_count': {'type': ['integer', 'null'], 'format': 'uint32', 'default': None, 'minimum': 0, 'description': 'Click count: 1 single (default), 2 adds dblclick, 3+ sets detail'}}}
session_clone
Derive a new browser session from a live one, carrying the full login state: cookies, localStorage/sessionStorage, viewport pin, dialog policy, proxy and keepalive flags. The source session stays untouched. Use to snapshot a logged-in state before risky actions, or to run the same login in parallel tabs. Returns {session_id (new), cloned_from, url, viewport}.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID to derive from (stays alive and untouched)'}}}
session_close
Close a browser session and free its resources. For a persistent session this also drops the on-disk login snapshot - idle expiry keeps it, an explicit close does not.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_console
Read the session's recent page console output (log/info/warn/error) as {url, total, matched, messages:[{ts_ms, level, text, url}]}, newest last. Ring buffer of 500 entries; captures output from page scripts, clicks, evals and navigation alike. Optional filters: level (exact, e.g. "error"), since_ts (epoch ms), url_contains (page URL substring), limit (most recent N matches). The fastest way to see WHY a page misbehaves: click the button, call this, read the error.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'level': {'type': ['string', 'null'], 'default': None, 'description': 'Only entries at this level: "log" | "info" | "warn" | "error"'}, 'limit': {'type': ['integer', 'null'], 'format': 'uint', 'default': None, 'minimum': 0, 'description': 'Keep only the most recent N matching entries'}, 'since_ts': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Only entries logged at or after this Unix epoch millisecond timestamp'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'url_contains': {'type': ['string', 'null'], 'default': None, 'description': 'Only entries whose page URL contains this substring'}}}
session_cookies
Export the session's current cookies. Default (meta absent/false) is the full Set-Cookie form ("name=value; Domain=…; Path=/", flags included) — the login-state reuse face that round-trips with session_create's cookies field. meta:true switches to the metadata-only view (#102): [{name, domain, path, secure, httpOnly, sameSite, expires (unix secs, null = session cookie), hostOnly}] with NO values — cookie values are credentials and never leave the server, so "which auth state exists" (is the session cookie Secure, when does it expire, which domains landed) is answerable without holding a single one.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'meta': {'type': ['boolean', 'null'], 'default': None, 'description': 'Metadata-only view (#102): {name, domain, path, secure, httpOnly,\nsameSite, expires, hostOnly} per cookie â\x80\x94 no values, ever. For\nchecking what auth state exists; leave false for the value-bearing\nexport that round-trips login state.'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_create
Create a persistent interactive browser session for multi-step interaction - clicking, typing, scrolling, reading state across page transitions. Use when the agent must INTERACT with a page (login flows, forms, pagination, click-through) rather than read it once. Returns session_id; persists 8 min idle. With persistent:true the login state survives idle eviction and server restarts - the same session_id revives logged-in.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'url': {'type': ['string', 'null'], 'default': None, 'description': 'Initial URL to navigate to (optional). `start_url` is honored as an\nalias (#115) â\x80\x94 callers guessing that name must not land on about:blank.'}, 'width': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': "Initial viewport width in CSS pixels. Pinned for the session's life\n(survives navigation) so element rects and media queries anchor to\nthe same layout across every page of the visit."}, 'height': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': 'Initial viewport height in CSS pixels.'}, 'mobile': {'type': 'boolean', 'default': False, 'description': 'Mobile device emulation (coarse pointer, no hover) for the initial\nviewport.'}, 'account': {'type': ['string', 'null'], 'default': None, 'description': "Run as a named login identity (the multi-account layer): a private\ncookie jar seeded from the account record, write-back to the account\nstore after every action. Concurrent logins (`taobao-scraper` vs\n`taobao-publisher`) never clobber each other. The account record\nsurvives the session â\x80\x94 a later create with the same name picks up\nthe warm jar, plus the record's captured localStorage/sessionStorage\n(replayed onto the captured origin; an explicit `storage` param\nwins). 1-64 chars of [a-zA-Z0-9_-]."}, 'cookies': {'type': 'array', 'items': {'type': 'string'}, 'default': [], 'description': 'Cookies to inject before navigation: `"name=value"` strings or\nCDP-style objects `{"name","value","domain",...}`. Lets the session\nstart already logged-in. Round-trips with session_cookies.'}, 'storage': {'description': 'Web Storage to inject after the initial navigation lands:\n{"local_storage": {"k":"v"}, "session_storage": {"k":"v"}}. For login\nstates that live in localStorage rather than the cookie jar. An\noptional "origin": "https://site" key holds the injection until a\nnavigation lands on that origin (a session created without a\nstart_url sits on about:blank first). Round-trips with\nsession_storage.'}, 'ttl_secs': {'type': ['integer', 'null'], 'format': 'uint64', 'minimum': 0, 'description': 'Idle time-to-live in seconds before the session is evicted\n(default: 480, clamped 60..3600). Raise it for long workflows.'}, 'keepalive': {'type': 'boolean', 'default': False, 'description': 'Exempt the session from the idle reaper: it lives until\nsession_close or server exit, so a workflow interrupted by long\nnon-browser steps keeps its login state.'}, 'use_proxy': {'type': 'boolean', 'default': False, 'description': 'Route through proxy (default: false)'}, 'persistent': {'type': 'boolean', 'default': False, 'description': "Persist the login state (cookies + localStorage/sessionStorage +\nviewport + dialog policy) to the server's local store after every\naction. If the session idles out â\x80\x94 or the whole server restarts â\x80\x94\nthe next call with the same session_id revives it logged-in\n(storageState-style recovery, no re-login). Explicit session_close\ndrops the snapshot."}}}
session_dialog
Inspect or flip the session's dialog policy for window.alert/confirm/prompt. Dialogs never block the page: each is auto-answered (default dismiss) and logged into session_console at level "dialog". action "list" reports {policy, prompt_text, dialogs}; "accept" makes subsequent confirm() true and prompt() return prompt_text (or the call's default argument); "dismiss" restores the default.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'action'], 'properties': {'action': {'type': 'string', 'description': '"list" reports the policy and dialog history; "accept"/"dismiss" set\nthe answer applied to subsequent window.confirm/prompt calls (alert\nis always logged, never blocking).'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'prompt_text': {'type': ['string', 'null'], 'default': None, 'description': 'With action "accept": text window.prompt returns once accepted\n(omitted keeps the current text).'}}}
session_drag
Drag the mouse from one viewport position to another: press at `from`, `steps` mousemove events, release at `to`. The trajectory is humanized by default (eased velocity, wobble, jittered timing, overshoot) — the shapes anti-bot checks score for; pass humanize:false for exact linear interpolation. Moves AMarker-style drag targets, canvas selections and captcha sliders that only track while the pointer travels.
Eingabeschema
{'type': 'object', '$defs': {'SessionXy': {'type': 'object', 'required': ['x', 'y'], 'properties': {'x': {'type': 'number', 'format': 'double', 'description': 'X coordinate in viewport CSS pixels'}, 'y': {'type': 'number', 'format': 'double', 'description': 'Y coordinate in viewport CSS pixels'}}}}, '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'from', 'to'], 'properties': {'to': {'$ref': '#/$defs/SessionXy', 'description': 'Where to release it'}, 'from': {'$ref': '#/$defs/SessionXy', 'description': 'Where to press the mouse button down'}, 'steps': {'type': ['integer', 'null'], 'format': 'uint32', 'default': None, 'minimum': 0, 'description': 'Interpolated mousemove events between from and to. Default: 24 with\nhumanize on, 10 without'}, 'delay_ms': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': 'Mean delay between moves in ms (default 18 humanized / 30 linear) â\x80\x94\nper-step timing is jittered around this when humanizing'}, 'humanize': {'type': ['boolean', 'null'], 'default': None, 'description': 'Humanize the trajectory: minimum-jerk easing, perpendicular wobble,\ntiming jitter, grip/settle pauses, occasional hesitation and\novershoot-and-correct. Set false when a test/tool needs exact linear\ninterpolation. Default: true'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_eval
Execute arbitrary JavaScript in a live browser session and return the result. Runs in the session's current page, so DOM mutations, globals and storage persist across calls — unlike the stateless eval tool, which loads its own throwaway page each call. Script-driven navigation moves the session's URL. JS exceptions are reported with name, line/column and stack.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'script'], 'properties': {'script': {'type': 'string', 'description': 'JavaScript code to execute'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'timeout_ms': {'type': ['integer', 'null'], 'format': 'uint64', 'default': None, 'minimum': 0, 'description': "Await budget for the script's promise in ms (default 5000, clamped\n100..120000). Pass a larger budget for slow page-side work such as\nuploads through the page's own fetch; on expiry the tool errors with\nEVAL_TIMEOUT (the script may still be running) instead of returning\na null result."}}}
session_export
Export a browser session's recorded action log. Format "bash" (default) returns a runnable curl script that replays every recorded action (navigate/click/input/scroll/eval) against a fresh session on this server — hand it to a shell or cron, zero model tokens. Format "jsonl" returns the raw action log, one JSON object per line. Format "json" returns a flow.json document — the same recording as editable ops ({op, args}) with cookies/storage stripped — that flow_run replays server-side.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'format': {'type': ['string', 'null'], 'default': None, 'description': 'Output format: "bash" (default) renders a runnable curl script that\nreplays every recorded action against a fresh session; "jsonl" returns\nthe raw action log, one JSON object per line; "json" returns a\nflow.json document (editable ops, cookies/storage stripped) for\nreplay via flow_run'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_input
Type text into an input/textarea element by its index (from session_state output), focusing it and dispatching input/change events. events:"full" is the complete human typing gesture: per-character keydown/keypress/input/keyup cycles, trailing change, then blur — the tail blur commits on forms that save in onBlur (React capture listeners, #100). In full mode a newline in the text types as the Enter key (key:'Enter', keyCode 13 — "type + Enter submit"): a textarea keeps the newline in its value, a single-line input stays single-line, the page's Enter listeners fire before the blur, and if the key wasn't canceled the input's form submits implicitly (Chrome's default action; preventDefault on the key or submit events vetoes it, so chat inputs that swallow Enter stay unsubmitted). Any characters — newlines, quotes, backslashes — ride through as-is. A refused fill answers filled:false with a reason (readonly/disabled/detached/no-element/wrong-tag/script-error) instead of a silent write. Hidden inputs are legitimate targets and are filled normally.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'index', 'text'], 'properties': {'text': {'type': 'string', 'description': 'Text to type into the input field'}, 'index': {'type': 'integer', 'format': 'uint', 'minimum': 0, 'description': 'Element index (from /state output)'}, 'events': {'type': ['string', 'null'], 'default': None, 'description': 'Event fidelity: "full" types one character at a time with a\nkeydown/keypress/input/keyup cycle per character, for pages whose\nlisteners key on keyboard events (e.g. keypress-Enter login forms).\nDefault fires a single input+change pair after the value is set.'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_list
List live browser sessions with idle age and the time left before auto-eviction. Use to discover a session to reuse instead of creating a new one; sessions expire after 8 min idle.
Nur Lesen
Eingabeschema
{'type': 'object', 'properties': {}}
session_navigate
Navigate a browser session to a new URL.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'url'], 'properties': {'url': {'type': 'string', 'description': 'URL to navigate to'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_network
Read the session's network request log. filter="media" extracts playback/stream URLs (m3u8/HLS, mp4, dash, flv...) actually requested by the page's player at runtime - the reliable way to get a real video link, since links embedded in page HTML are often decoys. Media elements and player iframes the engine never fetches (video/audio/source/iframe src) are merged in as candidates: via="network" entries are confirmed requests, via="dom" entries are candidates carrying their tag (iframes = kind "iframe", navigate into them to sniff). Default returns every request as compact rows (method/url/status/type/size/nav); include_headers=true adds each request's outbound header set to its row (#97). Each row's nav is the navigation generation that issued it and the payload's top-level nav is the current one - a lower row nav belongs to an earlier (e.g. timed-out) navigation attempt (#101). Navigate to the video page first, let it load, then call this.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'filter': {'type': ['string', 'null'], 'default': None, 'description': '"media" extracts playback/stream links (m3u8/HLS, mp4, dash, ...) from the requests the page actually issued - the reliable way to get a real video link, since URLs embedded in page HTML are often decoys. Media elements and player iframes the engine never fetches (video/audio/source src, iframe src) are merged in as candidates: entries carry via="network" (confirmed requests) or via="dom" (candidates, with their tag; iframes surface as kind "iframe" - player pages to navigate or sniff inside, not playable URLs). Omit to list every request as compact rows.'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'url_contains': {'type': ['string', 'null'], 'default': None, 'description': 'Narrow the `xhr` array to URLs containing this substring.'}, 'body_max_chars': {'type': ['integer', 'null'], 'format': 'uint', 'default': None, 'minimum': 0, 'description': 'Per-body character cap for the `xhr` array (default 4000).'}, 'include_bodies': {'type': ['boolean', 'null'], 'default': None, 'description': "Add an `xhr` array of background API responses (the page's own fetch/XHR\ntraffic with retained bodies) alongside the request rows â\x80\x94 the page's\nAPI face is often the cleanest structured read of its data."}, 'include_headers': {'type': ['boolean', 'null'], 'default': None, 'description': "Add each request's outbound header set to its row (`headers` on the\ncompact rows, `request_headers` on the `xhr` rows) â\x80\x94 what the page's\nJS actually sent, signed customs like x-s/x-s-common included. Off by\ndefault: headers can carry tokens."}}}
session_preload
Replace the session's document-start preload group (empty array clears). Sources run before each new document's own scripts — including inline <script> tags — which is the only hook that beats pages whose signing layer captures window.fetch/XHR natives at parse time (xhs's inline jsvmp). Set before the first navigate; applies to every navigation from then on.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'recipe': {'type': ['string', 'null'], 'default': None, 'description': 'Builtin recipe name appended after `scripts` (e.g. "xhs-sign"): the\nmaintained document-start wrapper for that site â\x80\x94 same source the\nengine auto-mounts on its navigations, without pasting JS. Unknown\nnames are an error, not a silent no-op.'}, 'scripts': {'type': 'array', 'items': {'type': 'string'}, 'default': [], 'description': "Full JS sources, in order. Sources run before each new document's own\nscripts (including inline ones) â\x80\x94 the only hook that beats pages whose\nsigning layer captures window.fetch/XHR natives at parse time. `[]`\nclears the group. Set before the session's first navigate and it\napplies to every navigation from then on."}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_screenshot
Screenshot the session's CURRENT DOM state (mutations from clicks/evals included) as a base64 PNG via the built-in renderer. Width/height default to the session's viewport, so session_viewport + session_screenshot shows the responsive layout. Returns {url, width, height, image_base64, format}.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'dpr': {'type': ['number', 'null'], 'format': 'float', 'description': 'Device pixel ratio (#185): rasterize at device resolution (Retina/HiDPI\nsharp) â\x80\x94 the bitmap comes back width·dpr Ã\x97 height·dpr with CSS geometry\nintact. Clamped to 1.0..=3.0 (default: 1.0)'}, 'width': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': "Render width in CSS pixels; defaults to the session's current viewport"}, 'height': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': "Render height in CSS pixels; defaults to the session's current viewport"}, 'selector': {'type': ['string', 'null'], 'description': "CSS selector: capture only that element's box"}, 'full_page': {'type': 'boolean', 'default': False, 'description': 'Capture the full scrollable page instead of the viewport (default: false)'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'selector_all': {'type': 'boolean', 'default': False, 'description': 'With selector, capture every match (default: first match only)'}}}
session_scroll
Scroll the page up or down by a number of viewport-heights.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'amount': {'type': 'integer', 'format': 'uint32', 'default': 3, 'minimum': 0, 'description': 'Scroll amount in viewport-heights (default: 3)'}, 'direction': {'type': 'string', 'default': 'down', 'description': 'Scroll direction: "up" or "down" (default: down)'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_set_files
Select files on a file input programmatically (Playwright setInputFiles semantics): builds File objects from base64 content, assigns them to input.files, then dispatches input+change so framework onChange handlers fire. Selector-addressed because file inputs are often hidden and absent from the session_state index.
Eingabeschema
{'type': 'object', '$defs': {'SessionFileSpecParams': {'type': 'object', 'required': ['name', 'content_base64'], 'properties': {'name': {'type': 'string', 'description': 'File name the page sees (and what multipart uploads as filename)'}, 'mime_type': {'type': ['string', 'null'], 'default': None, 'description': 'MIME type (default "application/octet-stream")'}, 'last_modified': {'type': ['number', 'null'], 'format': 'double', 'default': None, 'description': 'Last-modified time in ms since epoch (default: now)'}, 'content_base64': {'type': 'string', 'description': 'File content, standard base64 (padding allowed)'}}}}, '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id', 'selector', 'files'], 'properties': {'files': {'type': 'array', 'items': {'$ref': '#/$defs/SessionFileSpecParams'}, 'description': 'Files to select'}, 'selector': {'type': 'string', 'description': 'CSS selector for the file input, e.g. "input[type=file]". File inputs\nare often hidden, so this is selector-addressed rather than using the\n/state index.'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_state
Get the current page state as an indexed list of interactive elements. Returns compact text with [N] indexes for use with click/input tools.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_storage
Snapshot the session's localStorage/sessionStorage for the current origin: {url, local_storage, session_storage}. Feed it back via session_create's `storage` field to restore a logged-in state in a new session — the half of login state that cookies can't carry (many sites keep the session token in localStorage). Call before the session idles out.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_verdict
One call answers "where did this session land": verdict is one of challenge (risk control engaged — punish page or a 200-status API body that swallowed the wall; the response carries a handoff instruction for a human to solve it in the live view), captcha (explicit CAPTCHA interstitial), login (bounced to a login form — auth expired), empty, landed (normal 2xx content page), or unknown (couldn't classify — read facts; a non-2xx main document lands here with facts.doc_status carrying the number, so a zhihu-style burst 403 is branchable). The facts sheet also carries challenge_events, requests, console_errors and the fired signals. Pure code over signals the engine already holds (current URL, risk-control rows, main document status/size, console errors) — no screenshots, no page evals, single-digit milliseconds. Verdict observes, it never bypasses.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_viewport
Set the session's viewport (device emulation): scripts see innerWidth/innerHeight move, media queries like (max-width: 600px) re-evaluate, element rects re-anchor, and mobile=true flips pointer/hover matchMedia answers to coarse/none. Omitted width/height keeps the current value.
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'width': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': 'Viewport width in CSS pixels; omit to keep the current width'}, 'height': {'type': ['integer', 'null'], 'format': 'uint32', 'minimum': 0, 'description': 'Viewport height in CSS pixels; omit to keep the current height'}, 'mobile': {'type': 'boolean', 'default': False, 'description': 'Mobile emulation: matchMedia answers pointer:coarse / hover:none and\nnavigator.maxTouchPoints reports 5 (default: false)'}, 'session_id': {'type': 'string', 'description': 'Session ID'}}}
session_wait
Wait until a CSS selector matches or a JS predicate turns truthy, with a timeout. The page's event loop keeps running while waiting (fetches, timers, promise chains progress), so this replaces blind sleeps for async content: navigate, session_wait for '.price-card', then click/read. Returns {matched, elapsed_ms, detail:{tag,text} or the predicate value}; errors with `timeout ...` naming the selector/predicate on expiry. Exactly one of selector/predicate.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['session_id'], 'properties': {'selector': {'type': ['string', 'null'], 'description': 'CSS selector to wait for (e.g. ".price-card")'}, 'predicate': {'type': ['string', 'null'], 'description': 'JS expression polled until truthy (e.g. "document.querySelectorAll(\'.card\').length >= 3")'}, 'session_id': {'type': 'string', 'description': 'Session ID'}, 'timeout_ms': {'type': 'integer', 'format': 'uint64', 'default': 10000, 'minimum': 0, 'description': 'Give up after this many milliseconds (default: 10000, max: 120000)'}}}
Geändert
session_screenshot
1. October 2026 02:50
Geändert
session_preload
1. October 2026 02:50
Geändert
session_input
1. October 2026 02:50
Hinzugefügt
flow_search
1. October 2026 02:50
Geändert
session_network
29. September 2026 02:59
Geändert
session_create
29. September 2026 02:59
Geändert
session_cookies
29. September 2026 02:59
Hinzugefügt
flow_install
29. September 2026 02:59
Geändert
session_input
27. September 2026 02:50
Geändert
session_create
27. September 2026 02:50
Geändert
fetch
27. September 2026 02:50
Hinzugefügt
session_verdict
25. September 2026 02:59
Hinzugefügt
session_preload
25. September 2026 02:59
Geändert
flow_run
25. September 2026 02:59
Hinzugefügt
account_login
25. September 2026 02:59
Geändert
session_input
21. September 2026 02:57
Geändert
session_drag
21. September 2026 02:57
Geändert
session_click
21. September 2026 02:57
Geändert
session_challenges
21. September 2026 02:57
Geändert
session_wait
19. September 2026 02:48
Geändert
session_viewport
19. September 2026 02:48
Geändert
session_storage
19. September 2026 02:48
Geändert
session_state
19. September 2026 02:48
Geändert
session_set_files
19. September 2026 02:48
Geändert
session_scroll
19. September 2026 02:48
Geändert
session_screenshot
19. September 2026 02:48
Geändert
session_network
19. September 2026 02:48
Geändert
session_navigate
19. September 2026 02:48
Geändert
session_input
19. September 2026 02:48
Geändert
session_export
19. September 2026 02:48