"Toll" matching MCP servers:

Enables AI-powered generation of styled QR codes with 10 design presets, supporting single or batch creation with custom logos and formats (SVG/PNG) directly from AI tools.

Enables AI agents to perceive and quantitatively verify physical hardware through USB webcams and RTSP/HTTP network streams, returning inline image content plus numerical metrics such as brightness, contrast, edge density, motion, SSIM baseline comparisons, and OCR text. Agents can watch feeds for visual conditions, correlate buffered frames with serial/log/MQTT events, and apply privacy masks and access controls.

Enables local OCR transcription of images using tesseract.js, with optional low-token AI-generated descriptions, folder batch processing, and compatibility with MCP clients like ChatGPT, Claude, opencode, and Cursor.

Enables MCP clients to control Bosch Smart Home Cameras via natural language, including snapshots, motion events, privacy mode, and pan/tilt, using a reverse-engineered cloud API.

Enables interaction with Figma designs through the Figma API, allowing users to export images in multiple formats, extract style data and CSS, analyze design elements, and retrieve SVG code from Figma files. Supports batch operations and comprehensive design element analysis including images, vectors, and components.

Enables AI assistants to create Material Maker node graphs from natural language, validate them against the node catalog, and render them headlessly to PBR texture maps and editable .ptex files.

Enables agents to perform structured shopping actions and retrieve targeted product images for visual comparison, matching, and aesthetic recommendations.

Lets MCP clients search kie.ai's live catalog of 200+ generation models, inspect each model's schema, price and success rate, then prepare, approve and submit media generation plans that return the finished image, video, music or speech files. Paid runs stay behind an explicit prepare → approve → submit flow so credits are only spent once a plan is shown and accepted.

Enables AI agents to drive a local asset review loop: list and fetch paired original/output items (including image content for visual comparison), mark pass/reject/unsure with problem tags and region annotations, batch-review scoped selections, and export results as JSON or CSV. Also supports round archiving, detecting stale results after source re-renders, and listing previous-round rejects.

Enables AI assistants to access and control network cameras to capture images and perform analysis including brightness detection, color distribution, and edge detection.

Enables AI agents to source real, license-labelled photos and video clips of the exact person, company, product, or place named in a script, with each candidate checked by a vision model and scored before returning download links or capture commands. It also plans b-roll across a whole transcript, matching each moment to the words it plays over.

Enables an AI assistant to batch-drive ArmorPaint headlessly via its native CLI and scripting engine, re-exporting projects at different presets and building procedural materials without opening the GUI.

Lets an LLM see what's on your screen by capturing an entire monitor or a specific application window.

Enables OCR text extraction from images and PDFs via MCP tools, allowing multiple devices on a local network to use PaddleOCR without installing it locally.

MCP server that exposes ComfyUI image and 3D generation as a single tool with smart prompt classification. It enables AI assistants to generate assets directly by selecting and running the appropriate ComfyUI workflow.

Enables image and video processing through FFmpeg, including compression, format conversion, resizing, and batch processing operations for common media formats.

Enables intelligent identification and validation of compound data from documents and images, then automatically draws compound structures using local ChemDraw software with academic formatting.

A local MCP server for generative image description, providing prose captions, OCR, and LoRA dataset caption sidecars via Florence-2, with deterministic decoding and an honesty contract.