"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

MCP server providing 26 visual tools for text-only LLMs, enabling description, coordinate location, OCR, annotation, cropping/zooming, anomaly scanning, and computer control with switchable VLM backends.

Enables searching, inspecting, auditing, and composing AI video prompts using 150 verified prompts that were each rendered into real Seedance 2 videos.

Lets MCP hosts search the public Image3 GPT Image 2 prompt gallery, fetch complete prompts, list categories, and turn rough ideas into structured prompt briefs.

Enables deterministic, read-only design of OpenSora video prompts and shot plans, including prompt diagnosis and access to workflow guides, without generating videos or requiring API keys.

Enables deterministic, read-only construction of Seedance-oriented video prompts, planning of multimodal reference-aware sequences, prompt diagnosis, and discovery of canonical See Dance 2 resources.

Routes one brief to the right image model across 60+ (gpt-image-1.5, Ideogram 3, Recraft V4, Flux), validates the output, and fans out to iOS/Android/PWA/favicon/visionOS/Flutter bundles. Works without an API key via Pollinations, HF Inference, Stable Horde, or host-LLM inline SVG.

A read-only, deterministic server that enables assembling copy-ready video prompts, planning timed shot sequences, diagnosing prompt clarity and current duration/resolution/reference/end-frame/audio limits, and retrieving canonical creation, guide, pricing, and policy URLs.

Local MCP server offering an introduction tool and image generation from prompts using Azure OpenAI (gpt-image-2).

Enables Claude to create, modify, and manipulate Cinema 4D scenes through prompt-driven tools for primitives, objects, materials, lighting, cameras, animation, MoGraph, dynamics, and rendering.

Connects Claude to a Cinema 4D plugin via a socket bridge, enabling prompt-driven 3D scene creation and manipulation such as adding primitives, materials, lights, cameras, MoGraph cloners, dynamics, and rendering previews. Also exposes raw Python execution and Redshift material inspection inside the running Cinema 4D environment.

Enables text-only language models to understand images by forwarding image and prompt requests to vision model backends via MCP, returning descriptive text. Supports multiple OpenAI-compatible providers with task routing and safety checks.

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.

An MCP server that enables AI agents to search, retrieve, and curate free stock photos and videos from Pexels, with tools, resources, and prompts for easy integration.

Exposes OpenAI's gpt-image-2 and gpt-image-1.5 to Claude Code as a single tool for generating, editing, or composing images with automatic model selection.

Provides image recognition capabilities using Anthropic Claude Vision and OpenAI GPT-4 Vision APIs, supporting multiple image formats and offering optional text extraction via Tesseract OCR.

Provides vision capabilities to text-only LLMs by acting as a cloud vision adapter layer, enabling image understanding and OCR text extraction through a single MCP tool.

Enables analysis of an image's optical properties (color temperature, light vectors, luminance dynamics) and generation of physically grounded relighting variants, harmonized composites with contact shadows, and calibrated diffusion prompts for GPT Image and Nano Banana targets.

MCP server that connects an AI assistant to a running ComfyUI instance, allowing it to fetch saved workflows, inject a prompt and seed, run generation, and return the image inline in chat.

Enables AI agents to inspect and work with PDF files entirely on the local machine, covering page counts, metadata, layout, encryption permissions, scan-vs-text detection, and page rendering. Generated results land in a temporary workspace as short artifact ids that can be chained between tools and exported to real folders on request.

Enables drawing commands to be rendered into raster images, supporting shapes like lines, rectangles, circles, ellipses, and triangles, with results returned as inline PNGs or saved to files.

An MCP server that lets Claude Code generate videos using BytePlus ModelArk Dreamina Seedance 2.5, handling task submission, polling, and file downloads through plain language prompts.

Exposes OpenAI's gpt-image-2 (image generation and editing) as an MCP server for tools like generate_image, edit_image, and iterative edit sessions.

Enables AI image generation and editing using Google's Nano Banana model via the AceDataCloud API. It supports creating images from text prompts, virtual try-ons, and product placement directly within MCP-compatible clients.

Enables text-only reasoning models to see images by wrapping vision-language models as MCP tools, supporting image description, OCR, chart analysis, and custom questioning within MCP-compatible IDEs.

Lets coding agents such as Claude Code and Codex hand summarising, field extraction, classification and OCR to the free, offline on-device model for Apple Foundation Models on macOS 27. One Rust binary, installed with Homebrew.

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.

An MCP server that enables AI assistants to search royalty-free stock photos using natural language, example images, or similarity, and render results as an inline thumbnail grid.

Enables image analysis using any OpenAI-compatible vision API, supporting URLs, local files, or base64 input with custom prompts.

Enables AI agents to analyze images via Gemini vision models, supporting local paths, URLs, and data URLs with custom prompts.

Enables an AI assistant to conversationally control Autodesk AutoCAD, drawing, inspecting, and editing plans, and includes a cross-platform DXF engine that runs without AutoCAD on macOS and Linux. It exposes tools for rendering views as images, batching geometry, blocks, and structures, measuring and checking plans, and undoing whole batches.