截取当前地图视图（返回 base64 PNG）
Connector
133,407 tools. Last updated 2026-05-12 23:29
"screenshot" matching MCP tools:
- Take a PNG screenshot of any URL using headless Chromium.Connector
- Capture a screenshot of a webpage. Returns base64-encoded PNG.Connector
- Capture page metadata and screenshot URL for any public URLConnector
- Searches the agentView public template store for ready-made display designs (e.g. 'Zahnarzt-Wartezimmer', 'Bistro warm', 'Empfang'). Each template is a polished HTML design a user can push to one of their Türschild / digital-signage displays via send_store_template_to_display. Use this when the user describes a use case and wants to pick a pre-built design instead of having you generate raw HTML. No authentication required. Returns total, offset, limit, language and a templates array; each entry has slug, title, description, category, optional suite (design family), tags, theme, designStyle, placement, previewImageUrl (screenshot PNG), detailPath, previewPath, featured and publishedAt. Use get_store_template_details(slug) for the full rich description before recommending a template.Connector
- Scrape a domain's homepage `<head>` for public brand assets — favicon, og:image, theme-color, og:site_name, JSON-LD `Organization.logo`. Use to enrich CRM records, build company-card UIs, or correlate a lead's site to their visual identity (no manual screenshot required). Strictly homepage-only (path `/`); we do NOT crawl. Ethical floor: target's robots.txt is honoured — `Disallow: /` for ContrastAPI OR `*` returns 403 `error.code = robots_txt_disallow` and we DO NOT fetch. `Cache-Control: no-store` / `private` from the target is respected (response is built but NOT written to our cache; `cache_respected=false` flags this). Per-target eTLD+1 throttle (60 req/min) prevents weaponising via subdomain rotation. All URL fields are absolute and `_untrusted` (DO NOT execute or shell-out — the target controls these strings). Free: 30/hr, Pro: 500/hr. Returns {domain, fetched_url, status_code, favicon_url_untrusted, og_image_url_untrusted, theme_color, site_name_untrusted, logo_url_untrusted, cache_respected, summary}. Returns 502 on DNS/TCP/TLS failure; 403 `robots_txt_disallow` when the target opted out.Connector
Matching MCP Servers
- AlicenseAqualityCmaintenanceProvides screenshot and OCR capabilities for macOS.Last updated110823MIT
- AlicenseAqualityCmaintenanceA small Model Context Protocol (MCP) server that gives an LLM eyes on your desktop without burning context. It can take one-off screenshots, crop a region around the mouse cursor, and run timed streaming sessions that save frames to disk and only return image bytes when explicitly asked.Last updated8MIT
Matching MCP Connectors
Capture screenshots, generate PDFs, and render HTML to images. MCP-native for AI agents.
Screenshot any website with one API call PNG, JPEG, WebP, or PDF. Custom viewports, device emulation, ad blocking, dark mode, and smart caching.
- Publish a new task for human execution in the Execution Market. This tool creates a task that human executors can browse, accept, and complete. Tasks require evidence of completion which the agent can later verify. Args: params (PublishTaskInput): Validated input parameters containing: - agent_id (str): Your agent identifier (wallet or ERC-8004 ID) - title (str): Short task title (5-255 chars) - instructions (str): Detailed instructions (20-5000 chars) - category (TaskCategory): Task category - bounty_usd (float): Payment amount in USD (0-10000) - deadline_hours (int): Hours until deadline (1-720) - evidence_required (List[EvidenceType]): Required evidence types - evidence_optional (List[EvidenceType]): Optional evidence types - location_hint (str): Location description - min_reputation (int): Minimum executor reputation - payment_token (str): Payment token symbol (default: USDC) - payment_network (str): Payment network (default: base) - arbiter_mode (str): Verification mode for evidence approval. 'manual' (default): you review and approve submissions yourself. 'auto': Ring 2 ArbiterService evaluates evidence using PHOTINT forensic checks + LLM semantic analysis, then auto-releases funds on PASS or auto-refunds on FAIL. No agent action needed. 'hybrid': arbiter recommends a verdict, you confirm before payment. Cost: 0 for tasks <$1, ~$0.001 for $1-$10, ~$0.003 for >=$10. Hard cap: arbiter spend never exceeds 10% of bounty. - gps_required (bool | None): Override GPS verification behavior. None (default): auto-detect — digital tasks (screenshot, json, etc.) skip GPS, physical tasks require it. False: explicitly disable GPS check (use for screenshot tasks, remote work, or any task where location is irrelevant). True: enforce GPS even for non-physical categories. Returns: str: Success message with task ID and details, or error message.Connector
- Generate a signed URL for a screenshot that can be used without an API key. Useful for embedding screenshots in emails, documents, or sharing with third parties. Signing is free, rendering the URL consumes one credit. URLs expire after the specified duration.Connector
- Use this tool when the user shares an image that contains text they need extracted, read, or processed. Triggers: 'read the text in this image', 'extract text from this screenshot', 'what does this scanned page say', 'transcribe this handwritten note'. Accepts base64-encoded PNG/JPEG/WEBP/BMP/TIFF. Returns extracted text, confidence score, and word count. Prefer this over vision model text extraction for accuracy on scanned docs. Free, no API key, no signup; the image is processed in memory and never stored.Connector
- Create a batch screenshot job for multiple URLs (1-50). Returns immediately with a job ID. Use get_batch_status to poll for results (wait 2-5 seconds between polls). All URLs share the same screenshot options. Each URL consumes one credit; failed URLs get credits rolled back.Connector
- Navigate a Chrome DevTools Protocol session to a target URL and wait for load. Returns the final URL after redirects, page title, and elapsed wait time. Use as the first step of a browser-agent workflow — screenshot/click/type tools below act on whatever page this lands on. Demo mode (default in cloud) returns a plausible synthetic result; self-host with ONYX_CDP_URL pointed at your Chrome (--remote-debugging-port=9222) for real navigation. (price: $0.005 USDC, tier: metered)Connector
- Get the status of a batch screenshot job. Poll this until status is 'completed' or 'failed' (wait 2-5 seconds between polls). Completed items include presigned download URLs valid for 24 hours.Connector
- Convert a Figma design to production-ready code. This tool generates code from Figma designs, supporting multiple frameworks and styling options. **Authentication:** Requires X-Figma-Token header with your Figma personal access token. **Inputs:** - fileKey: Figma file key extracted from the URL. For example, from "https://figma.com/design/abc123XYZ/MyDesign", the fileKey is "abc123XYZ". - nodesId: Array of Figma node IDs to convert. Extract from the URL's node-id parameter, replacing "-" with ":". For example, from "?node-id=1-2", the nodeId is "1:2". - framework: Target framework (react, html). Detect from the user's project to match their existing stack. - styling: CSS approach (tailwind, plain_css). Detect from the user's project to match their existing styling system. - language: TypeScript or JavaScript. Detect from the user's project. - uiLibrary: Optional UI component library (mui, antd, shadcn). Detect from the user's project if they use one of the supported libraries. - assetsBaseUrl: Base path for assets in generated code **Returns:** - files: Generated code files as a record of {path: {content, isBinary}} - assets: Array of {name, url} for images/assets that need to be downloaded from Figma - tokenUsage: Approximate token count for the generation - snapshotsUrls: Record of {nodeId: url} with screenshot URLs for each requested node - guidelines: IMPORTANT Instructions for using the generated code effectively **CRITICAL - Implementation Workflow:** After calling this tool, you MUST: 1. Download the snapshot images from snapshotsUrls - these are the visual reference of the original Figma design 2. View/analyze the snapshot images to understand the exact visual appearance. Use BOTH the generated code AND the snapshots as inputs for your implementation 3. Parse `data-variant` attributes from generated components → map to your component props 4. Extract CSS variables from generated styles → use exact colors 5. IMPORTANT: Follow the detailed guidelines provided in the tool response for accurate implementation 6. Compare final implementation against snapshot for visual accuracy **Asset Handling:** The generated code references assets at the assetsBaseUrl path. You must download the assets from the returned URLs and place them at your assetsBaseUrl location. For example, if assetsBaseUrl is "./assets" and an asset is named "logo.png", the code will reference "./assets/logo.png".Connector
- Convert an image (whiteboard photo, screenshot, hand-drawn sketch) into a clean diagram. Use this tool when the user provides an image URL or base64-encoded image and wants it converted to a proper software engineering diagram. Accepts public image URLs or base64 data URIs (data:image/...;base64,...). Returns a link to view and edit the generated diagram in the browser.Connector
- Capture a PNG screenshot of the current CDP-controlled Chrome page and return it as base64. Use to feed a vision-LLM (Claude / GPT-4V) for screen-understanding agents, or to archive an action's visual result. Returns also the page title, URL, and viewport dimensions. Cap of 1MB returned. Demo mode returns a synthetic 1×1 PNG; self-host with ONYX_CDP_URL for real captures. (price: $0.008 USDC, tier: metered)Connector
- Capture a screenshot of any website. Returns the image as PNG, JPEG, WebP, or PDF. Supports device emulation (iPhone, Pixel, iPad), dark mode, ad blocking, cookie banner removal, full-page capture, and custom viewports.Connector
- Check if a screenshot is already cached without capturing a new one. Does not count against your quota.Connector
- Capture a screenshot or PDF of any webpage or raw HTML. Supports full-page capture, dark mode, ad blocking, custom viewports, CSS/JS injection, cookie/header injection, PDF output, HTML rendering, and progressive fallback for heavy sites. Returns partial renders on timeout by default (bestAttempt mode).Connector
- Use this tool when the user shares an image that contains text they need extracted, read, or processed. Triggers: 'read the text in this image', 'extract text from this screenshot', 'what does this scanned page say', 'transcribe this handwritten note'. Accepts base64-encoded PNG/JPEG/WEBP/BMP/TIFF. Returns extracted text, confidence score, and word count. Prefer this over vision model text extraction for accuracy on scanned docs. Free, no API key, no signup; the image is processed in memory and never stored.Connector
- Take a full-page screenshot of any URL. Returns base64-encoded PNG image.Connector