"Cargo Doc" matching MCP servers:

Reads passports, ID cards and driver's licences from a photo or scan and returns the printed fields and MRZ as structured JSON. One credit ($0.01) per recognised document; nothing is charged when no document is found.

A local MCP server that provides OpenAI GPT text generation and image generation over standard input/output.

Smart Doc MCP Server that enables AI agents to read web pages (with or without browser, supporting login and SPA) and perform OCR on clipboard images.

Enables automated OCR and Thai tax invoice processing from PDFs and scanned images, including parsing key invoice fields, three-tier routing, SQLite storage, and human review workflows via MCP tools.

Enables agents to create, inspect and edit Kdenlive project files, import and relink media, query installed MLT effects/transitions, author subtitles, and run asynchronous MLT renders, plus drive the live Kdenlive editor UI. Edits always write new files, and rendering is job-based with verification of the output.

Typed DCC-MCP control for Marmoset Toolbag 4.03+ and 5.x, enabling shell-capable agents to interact with Toolbag scenes via a shared CLI and MCP gateway.

Enables AI clients to control Blender's 3D workflow via an embedded MCP server.

Enables reading images (diagrams, screenshots) directly via the model's own vision, with no external API key needed, and can extract embedded images from .doc/MHTML documents.

Enables users to create, inspect, edit, and export bounded synthetic 3D Slicer volumes, phantoms, and sphere meshes, configure cameras and orthogonal slices, and render PNG previews via MCP. It also supports native MRB scene round-tripping and NRRD/STL artifact export within a trusted local workspace.

Enables AI agents to drive a persistent, isolated ParaView session for scientific visualization: creating and editing spheres, clipping with planes, importing single-file VTI/VTP/VTU datasets, extracting contours, exporting verified datasets, saving native PVSM states, and rendering display-backed PNG previews. All operations are confined to a single operator-owned workspace on a Linux-only, display-backed host, with no attachment to existing GUI pipelines.

Exposes a typed headless editing surface for PhotoCraft documents, letting clients create, open, inspect and save RGB8 files while working with layers, masks, selections, adjustments, text, transforms, fills, previews, exports and bounded noise reduction through 39 typed tools. It manages an official PhotoCraft stdio process with validated schemas, isolated workspace paths, resource limits, and explicit recovery semantics for indeterminate edits.

Adobe Photoshop adapter bridging AI agents (Claude, Cursor, Copilot) to Photoshop via UXP WebSocket for document and layer management.

Enables typed, auditable control of CapCut Desktop through a localhost, token-authenticated bridge and bundled CapCut-side panel, covering project setup, media import and proxies, timeline and clip editing, transitions, text and auto-captions, audio mixing, effects and color, AI helpers, and video or thumbnail export. Also includes guided installation and environment verification plus a repeatable vlog assembly recipe.

Enables AI assistants to remotely control Sony DSC cameras via the Camera Remote API, supporting live view, shooting, exposure adjustment, zoom, and content management.

MCP adapter for Adobe Illustrator enabling structured DOM inspection and editing of documents, artwork, and exports via DCC-MCP CLI.

Enables AI agents and terminals to generate images, video, and audio using 141 models from 28 providers via the Picsart gen-ai API.

Enables MCP clients to search and inspect an invoice ledger, generate VAT summaries, run OCR on local documents, and use reusable prompts for chasing overdue invoices and reconciling entries.

An MCP server that generates images of random dogs from the Dog CEO API with 'LGTM' text overlaid. It allows users to create and save these images to a specified local path through natural language commands.