All 49 tools
The complete VidMee tool surface. Over MCP these are tool calls; over REST each is
POST /v1/jobs {"operation": "<name or alias>", "input": {...}}. Names are
underscore-cased for the tool-use API; the dotted alias also works as a REST operation.
edit_image, inspect, report, storyboard_video, sweep_site, test_flow, verify_against_reference. Each fuses many primitives into one verdict, so one call usually replaces five.QA & flows
inspect
heroqa.inspectRender a page (or drive an open session) and return ONE fused verdict: UI/UX critique, real axe-core WCAG, runtime errors, visual-memory regression check, and next actions. The hero call.
sweep_site
heroqa.sweep_siteCrawl a whole site and judge every page: per-page findings plus a severity rollup. Baselines live in memory so re-renders diff against last-known-good. Nightly QA in one call.
test_flow
heroqa.test_flowDrive a scripted multi-step browser flow (click, type, navigate) and return a pass/fail verdict with per-step evidence. Logged-in journeys included.
Perceive
analyze_document
specialistperceive.documentRead a PDF or design export into structured data.
analyze_screenshot
specialistJudge a screenshot you already have (send local files as image_base64). Returns critique + asset_id.
analyze_video
specialistperceive.videoJudge a video journey frame-by-frame.
analyze_visual
specialistperceive.analyzeAnalyze a stored asset by id against your questions.
capture_element
specialistFull-resolution screenshot of a single element by selector (e.g. lift a logo).
check_crawlability
specialistperceive.crawlabilityMeasure how much of a page is invisible to no-JS crawlers and AI agents (AEO readiness).
creative_self_qa
specialistperceive.creative_qaOne-call creative gate: aspect ratio + brand fidelity + text/quality in a single verdict.
extract
specialistperceive.extractSchema-guided structured extraction: pull typed fields off a rendered page.
og_check
specialistperceive.og_checkValidate OpenGraph / Twitter share-preview meta and image.
render_and_analyze
specialistperceive.renderRender a URL/HTML and return a UI/UX + accessibility critique with concrete fixes, deterministic runtime-error findings, and a signed screenshot URL.
validate_responsive
specialistperceive.responsiveFlag layout breaks, overflow, and hidden CTAs across viewports.
Compare
verify_against_reference
herocompare.verify_referenceGrade a candidate against a real reference (mock, brand, prior screenshot) for fidelity. Catches convincing fakes that aesthetic QA passes.
compare_screenshots
specialistcompare.screenshotsPixel + semantic diff of two stored assets for regressions, with changed regions.
Memory
create_baseline
specialistPin a stored asset as a named baseline to diff future renders against.
find_similar_visuals
specialistmemory.similarTrue image-to-image similarity (DINOv2) for 'more like this' and near-duplicate / regression detection.
ingest_visual
specialistmemory.ingestPull an external image into visual memory with tags and an optional TTL.
list_baselines
specialistList the baselines saved for your project.
search_visual_memory
specialistmemory.searchSemantic search over remembered assets.
Generate & create
edit_image
herogenerate.editEdit a REAL photo from a plain instruction while preserving the real product/branding and designing the rest. Built-in fidelity gate + retry. Nano Banana or FLUX Kontext.
storyboard_video
herogenerate.storyboardShot list to one finished multi-shot video: generate every shot through the gen-quality path, then stitch. Camera direction + supplied audio.
compose_video
specialistgenerate.videoAssemble finished video from clips/frames (+ motion, transitions, supplied audio, burned captions).
composite_image
specialistgenerate.compositeDeterministic overlay on a real photo: text, logo, or clone-remove a region. Swap branding pixel-exactly.
generate_until_pass
specialistgenerate.until_passRegenerate until it passes a quality/fidelity bar; escalates across providers and returns the best attempt even if none fully pass.
generate_visual
specialistgenerate.visualText to image/video via the best provider (Zark/fal/Replicate), with task-aware model + tuned params. Pass provider to force one, quality_hint for cinematic.
list_models
specialistThe model catalog: per media, per task, which model each provider uses + tuned params.
list_providers
specialistDiscover the generation providers, what each is best for, and how to override.
render_template
specialistgenerate.templateDeterministic on-brand statics (cards, OG images) from a template + tokens.
Report & tickets
report
heroreport.buildTurn an inspect/test_flow result (or a source URL) into a structured markdown QA report.
create_ticket
specialistFile a finding straight into GitHub / Linear / Slack from a QA result.
link_asset_to_issue
specialistTie a finding to a tracker issue (GitHub/Linear/etc).
Browser (low-level)
browser_act
low-levelAct in the session: click / type / select by ref or selector.
browser_close
low-levelClose the browser session and free the resource.
browser_observe
low-levelReturn a compact semantic read of the current page (not raw DOM) with actionable refs.
browser_open
low-levelOpen a persistent, stateful browser session the agent drives across steps (optionally restoring saved auth).
browser_save_session
low-levelSave the session's auth/storage state for later reuse (logged-in flows).
browser_screenshot
low-levelScreenshot the current session state.
Account & results
delete_login
specialistDelete a vaulted login by name. Cost: free (utility/read).
estimate
specialistPrice a job BEFORE running it — no job created, no charge (#4). Generation is pass-through provider cost + margin (an estimate that settles on the real cost); analysis is a flat credit price. Pass the same `operation` + `input` you'd send t
get_brand_kit
specialistRead one stored brand kit (palette, wordmark, style, logo asset) by slug. Cost: free (utility/read).
get_result
specialistFetch the result of a long-running job by id.
get_wallet
specialistCheck analysis-credit and generation-cash balances before spending.
list_brand_kits
specialistList this project's stored brand kits (slug + name + palette + style). Pass a slug as `brand_kit` to generate_visual (with a `template` + `title`) to produce in that house style — no hand-carried brand prompt. Create/extract kits via the RE
list_logins
specialistList your vaulted logged-in sessions (names + domains + expiry — never the stored credentials). Pass a name as login="<name>" to browser_open / test_flow / inspect. Cost: free (utility/read).
record_outcome
specialistTell VidMee whether a prior judgment was right (confirmed_real / fixed / false_positive). How accuracy is proven.
save_login
specialistVault a LOGGED-IN browser session under `name` so you can resume authenticated QA/browsing by name later — log in ONCE, reuse forever (no re-holding cookies). Three ways to provide it: `from_session_id` (capture a live browser_open session