Enables AI agents to programmatically edit videos via FFmpeg, providing tools for probing, trimming, concatenating, timeline composition, LUT generation/application, rendering, and edit verification over MCP.
Enables AI assistants to control DaVinci Resolve (Free and Studio) through natural language, providing 162 tools for timeline editing, color grading, rendering, and more. Includes local AI replacements for Studio-only features like voice isolation, background removal, and transcription.
Enables AI clients to inspect and edit game item databases, validate workspaces, render pixel icon atlases, roll loot, simulate shop and crafting rules, and export Godot or PixiJS assets over stdio or HTTP.
A zero-cost, China-accessible MCP server providing four free AI capabilities: text chat, image generation, speech-to-text, and text-to-speech, ready to use after cloning.
Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.
Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language.
Enables MCP clients to discover OpenRouter image and video models, generate and edit images, create variations, launch and monitor video jobs, and save resulting media into authorized local project directories with cost controls.
Enables MCP clients to generate images through multiple free/low-cost providers with automatic failover, plus session history, provider status, and configuration tools.
Privacy-first MCP server for macOS that allows AI agents to search local images using natural language descriptions, leveraging MLX CLIP embeddings and LanceDB for fast, fully offline search.
Enables natural language search of local photo archives using AI-powered semantic understanding, with integration into Claude Desktop via the Model Context Protocol.
An MCP server that searches the web for images, creates a numbered contact sheet for visual selection, and downloads the chosen images with provenance metadata. Works without an API key.
Enables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.
Enables MCP clients such as Claude Code, Codex, or Pi to search for existing images through ZCode's search_image interface using required query, count, gl, and rank parameters. It does not generate images.
Connects an AI agent to Adobe Photoshop through COM/ExtendScript so it can build and correct designs —layers, typography, vector shapes, layer effects, blend modes, masks, adjustments and filters— while previewing its own output, inspecting a document's resources, and learning a reusable style from the user's finished PSDs.
A customizable Model Context Protocol server implementation that enables AI models to interact with external tools including weather queries, Google search, and camera control functionality.
Enables AI assistants to programmatically inspect projects, create compositions and layers, apply effects, animate properties, and manage render jobs in Adobe After Effects through natural language.
Enables WorkBuddy and other MCP-compatible clients to generate images and videos from natural-language prompts through Agnes AI, returning online URLs and locally saved files.
A server that allows AI tools like Claude and Cursor to automate and control Photoshop through natural language commands, enabling tasks like editing PSDs, toggling layers, and generating marketing creatives.
Enables agents to identify the exact catalogue SKU from a customer photo using image retrieval and optional vision-LLM re-ranking, then check live inventory with tenant-aware safeguards.
Enables LLMs to drive Blender through socket-based two-way communication, letting them create and modify 3D objects, apply materials, run Blender Python, and fetch or generate assets while visually verifying results. Supports prompt-assisted 3D modeling, scene creation, and manipulation.
Enables AI agents to search for reference images using natural language queries, aggregate results from multiple image sources, and interactively select, refine, and download images through tool calls.
An MCP server for generating images and checking generation status through ComfyUI's API. It allows interaction with local ComfyUI instances by providing workflow-based image generation and status checking tools.
Enables AI agents to analyze images from a URL, local path, or Base64 string and determine whether they are AI-generated, including detection of signatures from Flux, Midjourney, DALL·E, and Stable Diffusion. Also inspects cryptographic C2PA provenance manifests, signing certificate authorities, and camera EXIF metadata without requiring API keys or accounts.
A Model Context Protocol server that provides web and image search capabilities through Google's Custom Search API, allowing AI assistants like Claude to access current information from the internet.
Enables AI assistants to control a Blender instance through MCP tools, supporting scene creation, editing, and asset exchange via HTTP and background CLI processes.
Provides tools to fetch IIIF manifests and retrieve specific image regions or scaled images for analysis. This server enables detailed interaction with International Image Interoperability Framework resources, supporting tasks like image description and transcription.
Renders validated declarative scene specifications into MP4 videos inside disposable, network-disabled containers, then serves an embedded player with playback controls and diagnostics through MCP Apps. Users can iteratively revise scenes conversationally, with revision history preserved and identical renders reused per account.
Serves read-only tools that let an agent inspect PDFs step by step: outline a document, search for text or figure values, read pages and tables in order, describe figures and chart data, and render page or block images, with every block cited to its page and bounding box. It also lists the PDFs available under a configured root folder, which it never reads outside of.
A FastMCP server implementation that provides a standardized interface for accessing AI models hosted on Replicate's API, currently supporting image generation with customizable parameters.
Enables Claude to write, summarize, translate and classify text with optional Google Search sourcing, generate or edit images from up to three references, analyze images to extract text or read tables and invoices, and list the models an API key can access. It runs remotely on Cloudflare Workers so claude.ai custom connectors can reach it without maintaining a local server.
A read-only, local MCP server that enables Claude Desktop and Claude Code to brief users on selected WhatsApp chats, surfacing mentions, urgent items, follow-ups, bills, and payment screenshots through local OCR while keeping data encrypted on the user's PC.
Enables AI assistants to create and manipulate 3D scenes, objects, and materials, execute Blender Python, capture visual verification views, and generate or import assets and models.
Enables ChatGPT users to search and browse a private photo library, inspect metadata, and receive real image previews through read-only tools, while keeping encrypted sessions server-side.
Lets AI assistants and editors read documents on the local machine, turning PDFs, scans, invoices, receipts and bank statements into structured fields, line items and entities over stdio. Runs fully self-hosted with no cloud calls or API keys, so sensitive files never leave the user's machine.
A template MCP server that provides job searching tools (analyze descriptions, fetch postings, search opportunities) and basic image processing capabilities. Includes built-in authentication and is designed to work seamlessly with Puch AI.
Provides job search capabilities including analyzing job descriptions, fetching job postings from URLs, and searching opportunities, plus basic image processing tools like converting images to black and white.
Enables an AI assistant to read and build a running TouchDesigner network, including inspecting and wiring operators, editing GLSL/DATs, mapping MIDI, importing Shadertoy/ISF shaders, publishing to Resolume over Syphon/NDI and OSC, and diagnosing silent failures.
Lets MCP clients such as Claude, Cursor, Cline and Windsurf turn a text prompt or a public photo URL into a video clip with a soundtrack, returning a run id and then the finished file's URL, and also checks remaining account credits. Runs locally over stdio via npx or against a hosted Streamable HTTP endpoint using an API key.
An unofficial MCP server that runs inside Blockbench, enabling AI assistants to create, edit, inspect, texture, animate, review, and export 3D models through 204 modeling, rendering, quality-check, and format-integration tools.
Runs a Model Context Protocol server directly on Axis cameras, enabling any MCP-capable AI to inspect and control the camera without cloud or middleware.
Lets Claude and other MCP clients generate images with the OpenAI Images API and save them to a chosen path on disk, returning only the file path so no image data enters the conversation. Supports configurable quality, size, background, output format, and model, with transparent-background and error-reporting handling.
Enables MCP clients to operate local Adobe Premiere Pro projects, covering media ingest, bins, sequence and timeline editing, transitions, effects, keyframes, captions, markers, metadata, proxies, multicam, color, audio, and exports through 283 discoverable tools, 13 context resources, and 10 guided prompts. A bundled CEP panel provides the supported production bridge, with read-only connection verification and higher-level workflows for assembling product spots and motion-graphics demos.
Enables AI clients to drive local video editing projects through a CEP bridge, covering media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports across hundreds of discoverable tools. Ships context resources, guided prompts, and higher-level assembly workflows for agent-driven editing.
Enables AI-driven creation of savable Wallpaper Engine web wallpaper source projects through a local STDIO service, with bounded project discovery, revision-checked file edits, checkpoint restore, validation, and publish staging. It also opens managed preview windows to set public properties and capture screenshots and bounded logs as runtime feedback from the official engine.
Enables AI agents to inspect and drive Blender scenes directly, either through a live editor bridge on port 8190 or automatically via headless background CLI when Blender is closed. Provides token-efficient tools for scene outlining, object creation and modification, modifiers, materials, rendering, asset export, and arbitrary bpy script execution.
Enables coding agents to inspect and manipulate video and audio through ffmpeg-backed tools for probing, trimming, cropping, resizing, extracting audio or frames, generating thumbnails, normalizing loudness, concatenating files, burning captions, and converting formats. Each operation returns concise JSON with output path, size, and verified duration or dimensions.
Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.
MCP server that lets AI assistants control Adobe After Effects - ExtendScript execution, background rendering, and deep project/layer inspection - with first-class Arabic/RTL and multilingual support. 44 tools.
Provides access to the Ghibli Image Generator API for creating Ghibli-style images using OpenAI models. It enables users to generate stylized artwork through the ghibli_generate_image tool.
Enables Claude to inspect and build compositions in an open Adobe After Effects project, animate layers and effects, preview real frames, compare against reference video side by side, measure and recreate camera moves, detect cuts and beats, and render MP4s.
Enables AI clients to drive local Premiere Pro projects end to end — project setup, media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports — plus local ffmpeg/Whisper compute tools. Every mutating tool verifies its own result by readback, fingerprint, or a composited program-monitor frame, refusing to claim success it cannot confirm.