Capture a screenshot of the current browser or mobile screen, returned as a base64-encoded image resized for model context limits.
MIT
134,386 tools. Last updated 2026-05-13 22:08
"A search for image displays or exhibits" matching MCP tools:
- Scrapes Google Images search results with filters for size, color, type, safesearch, and domain. Returns image URLs, thumbnails, dimensions, and source page URLs for visual asset discovery and dataset collection.MIT
- Parse a recipe from a URL, free-form text, or image into structured ingredients, nutrition, and instructions for building a shopping cart.MIT
- Upload a local image file to Google Ads as an image asset for Responsive Display Ads or image extensions. Validates file size (max 5 MB) and extension (jpg/jpeg/png/gif). Returns asset resource_name, id, and display name.Apache 2.0
- Retrieve the profile photo for a Signal contact or group. Pass a phone number (E.164) or group ID to get base64-encoded image data.MIT
- Create a single-image Meta Ads ad creative by providing a destination URL, Facebook Page, and image (URL or hash). Optionally add headline, body text, and call-to-action. Returns the creative ID and object story ID for use in ad sets.Apache 2.0
Matching MCP Servers
- FlicenseAqualityCmaintenanceA Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.Last updated292
- FlicenseDqualityCmaintenanceA simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.Last updated16
Matching MCP Connectors
Search PubMed and summarize biomedical literature — designed for AI health agents.
Give your AI agent a phone. Place outbound calls to US businesses to ask, book, or confirm.
- Submit a receipt image or PDF for asynchronous AI extraction of receipt data. Receive a job ID to poll for status, with optional webhook notification. Returns extracted data for further processing.MIT
- Capture screenshots of web pages for visual verification of UI state, layout, or rendering. Supports full-page or viewport captures with configurable image formats.MIT
- Apply iterative improvements to the last image generated or edited in your session. Automatically uses the previous image without requiring file paths, enabling continuous refinement through text-based change descriptions.MIT
- Search NASA's public image, video, and audio library by keyword to access space exploration media with quality-scored results and verifiable citations.
- Transform an input image into a new image guided by a text prompt, adjusting the influence of the original image with a strength parameter.MIT
- Generate QR code images for text or URLs using the goQR.me service. Returns a PNG image link with quality verification and source attribution for data integrity.
- Displays welcome information about WayStation when the user says hello.MIT
- Upload an image to ComfyUI for use in img2img, ControlNet, or IP-Adapter workflows. Accepts a source URL or base64-encoded data, returns the stored filename for LoadImage nodes.MIT
- Upload a file or image to a row by providing base64-encoded data. Attach the file to a specified column, appending by default or replacing existing files when replace is set to true.MIT
- Generate an image from a text prompt, guided by a preprocessed ControlNet conditioning image such as pose, depth, or edge maps.MIT
- Removes the background from an input image, returning a raster image with the background removed. Accepts a URL or local file path.MIT
- Retrieve a summary of recent research samples with essential information for dashboard displays, using configurable time windows and result counts.AGPL 3.0
- Resizes images stored in Qiniu Cloud by specifying width or height while maintaining aspect ratio, returning a URL for direct access to the scaled image.MIT
- Search for AI workflows by name or keyword to find image generators, text processors, and other tools hosted on Glif.MIT