Shows a process tree with parent-child hierarchy and depth information, enabling you to trace spawned children and understand process relationships. Optionally filter to a specific PID's subtree.
MIT
744,618 tools. Updated 2026-11-04 23:54
"A method to allow vision models to process and understand image files" matching MCP tools:
- Capture the current chart as a base64 image to share, confirm placement, or feed a vision LLM. Requires explicit user opt-in due to high token cost.Apache 2.0
- Generate images with AI models for your designs. Supports text-to-image and image-to-image, returning workspace URIs for use in edits.MIT
- Extract still frames from video files via direct URL, producing storyboards, scene cuts, or evenly spaced frames with timestamps and a contact sheet for vision models and thumbnails.MIT
- List finished 3D models by date, showing task IDs, types, and downloadable formats; defaults to image-to-3d results, with task_types to include more.MIT
- Retrieve the complete JSON schema for image generation jobs. Understand all available options, constraints, and examples to create valid configurations.MIT
Matching MCP Servers
- AlicenseAqualityCmaintenanceEnables pure text LLMs to understand images by acting as a proxy to vision models via OpenAI-compatible APIs. Supports local files, URLs, and base64 inputs for image analysis.2MIT
- AlicenseNot gradedqualityCmaintenanceTurns a single image of an object into a textured 3D model (GLB with web-ready copy and six-view previews) on your own NVIDIA GPU, returning the written files and a preview. Runs locally as an MCP tool or, optionally, offloads the job to hosted GPUs with an API key.3AGPL 3.0
Matching MCP Connectors
Convert PNG, JPG and WebP images to SVG vector paths. Runs on Apify, $0.01 per image.
- Image to Text OCROAuth
OCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.
- Run a prompt across several models in parallel to compare answers and build ensembles.MIT
- Verifies whether an LLM's answer about an image is grounded in visible facts. Extracts up to three claims and checks each against the image, returning a score based on accurate claims.Apache 2.0
- Retrieve the Code-Me brand identity to understand its core mission and vision, including naming, philosophy, and tagline.MIT
- Discover available model categories to filter and browse models by type, such as text-to-image or image-to-video.MIT
- Lists Gemini models available to your account, showing display names and IDs. Use a returned model name to override the default in image generation or editing.MIT
- Inspect a Docker image's layer history to reveal build commands, sizes, and creation times. Use it to understand what an image is built from.MIT
- Capture the screen or a single window as an image to inspect colors, layout, and rendered UI; crop, apply vision filters, or take bursts for motion.MIT
- Generate AI images or videos asynchronously by submitting a task and polling for the result. Supports text-to-image, image-to-video, reference-to-video, and video editing models.MIT
- Discover which AI models are available on your NVIDIA account. Filter by capability code, vision, reasoning, or embedding to find the right model.MIT
- Find AI models by filtering tags like text-to-image or video-to-video and text queries. Returns name, tag, and route for each model matching the criteria.MIT
- List models available on your API key and identify which ones the server defaults to for image generation and vision tasks.MIT
- List active agent model access rules to control which LLM models each agent can use. Rules use glob patterns with deny taking precedence over allow.MIT
- Generate images from text prompts with Stable Diffusion models, optionally set model and dimensions, and return the image; list available models and prices on request.MIT
- Offload text generation to a chosen local AI model to reduce cost and keep data private; supports system prompts, JSON/JSON-Schema output, vision inputs, and streaming progress.Creative Commons Attribution Non Commercial No Derivatives 4.0 International
- 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