Multimedia Process MCP servers

A Model Context Protocol server for FileToPDF. It lets any MCP client — Claude Desktop, Claude Code, Cursor, Cline, VS Code, ChatGPT, n8n, Make, or your own agent — convert files, HTML, and Markdown to PDF through natural language: invoices, reports, documentation, DOCX/XLSX/PPTX, images, web pages, and more. Bring your own API key — get one free, in one click, at <https://filetopdf.dev> (10 free conversions, no signup required). Each convert tool returns a metadata summary and the PDF as an embedded application/pdf resource (base64), so capable clients can save the file. Set the FILETOPDF_OUTPUT_DIR env var, or pass save_path, to also write the PDF to disk.

5 tools · convert_file, convert_html

Drive Google Flow from an agent: Veo text-to-video, image-to-video and clip extension, Imagen text-to-image, reusable Characters and scene composition. Runs against your own Google account with Flow access; video generation bills your credits.

Generates app icons, favicons, OG images, logos, and wordmarks. Routes each request across 30+ image models. Runs without an API key via Cloudflare Workers AI, NVIDIA NIM, HuggingFace, or Stable Horde. Three modes: inline SVG, external prompt-only, or full API. Validates contrast, OCR text accuracy, and palette before returning.

Local OCR and image analysis via Apple Vision Framework. Wraps macOS's native Vision API to expose OCR for images and PDFs (with reading-order paragraphs, bounding boxes, line/paragraph IDs, and confidence), face / barcode / QR / document-corner detection, and image classification — all as MCP tools any client (Claude Code, Claude Desktop, Cursor, Codex CLI) can call. ~97% token savings vs sending raw images. Fully offline, no API keys, files never leave the Mac. One-line install: `npx -y macos-vision-mcp`.

Image generation and editing plus video generation (Veo, Sora, Seedance) via OpenRouter or any OpenAI-compatible API. Saves files to disk with token-cheap inline previews, resumable video jobs, live model listing, and a config-diagnostics tool. `npx -y mediamcp`.

The first MCP server for Final Cut Pro. 53 tools that parse, edit, and generate FCPXML timelines — health checks, flash frame detection, chapter markers, rough cuts, NLE export. 912 tests, MIT licensed.

Audio mastering for AI agents: LUFS/True Peak targets for Spotify and podcasts, Suno/Udio AI-fingerprint removal, mastering passport in chat (hosted server)

Loudness compliance verdicts for media files against formal broadcast standards (EBU R128, ATSC A/85): pass/fail with per-metric deltas, spec citations, and the exact ffmpeg remediation command. CLI and MCP over one engine; zero-install via `uvx --from 'loudcheck[mcp]' loudcheck --mcp`. Requires ffmpeg.

TypeScript MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation, editing, and asset downloads.

Turn YouTube videos into short-form clips from any AI assistant. AI-powered highlight detection, subtitle generation, 9:16 reframing, and direct download URLs via the Crabcut API.

Is this song AI or human? Detect AI-generated music (Suno, Udio) and media from any AI agent. Returns a verdict, AI-probability score, confidence, and provenance signals (Content Credentials / SynthID), plus scan_catalog to audit a whole music folder.

Unified Gemini media generation: Nano Banana (images, editing, multi-reference composition), Veo 3.1 (video, image-to-video, extend), TTS, and Lyria 3 (music with vocals). Single Go binary, 12 tools, supports Gemini API key and Vertex AI.

All-in-one multimodal MCP for 300+ OpenRouter models: text chat, image / audio / video analysis, and image / audio / video generation (Veo 3.1, Sora 2 Pro, Seedance, Wan). Structured `_meta.code` error taxonomy, IPv4+IPv6 SSRF guards, path-sandbox for disk writes, retry-after-aware backoff, multi-arch Docker.

Glif's official hosted media-generation agent: generate images, video, and audio, transcribe, and chain multi-step media workflows from natural language. Remote server at https://glif.app/api/mcp (OAuth).

Comprehensive Sonos audio system control through pure TypeScript implementation. Features complete device discovery, multi-room playback management, queue control, music library browsing, alarm management, real-time event subscriptions, and audio EQ settings. Includes 50+ tools for seamless smart home audio automation via UPnP/SOAP protocols.

AI image enhancement (upscaling, denoising, sharpening) via Topaz Labs API. Supports 8 models including Standard V2, Wonder 2, Bloom, and Recover 3.

AI-powered music production in REAPER through natural conversation - 173 tools across 26 modules covering transport, tracks, MIDI (insert/edit/quantize/humanize), mixing and FX (EQ, compression, sidechain, sends), tempo maps, markers/regions, ReaScript discovery/execution, and more.

AI-powered video editing MCP server with 10 tools for timeline editing, 5-layer compositing, semantic operations, and FFmpeg rendering (1920x1080, 30fps H.264+AAC).

Drive a real desktop NLE from any MCP client: place/trim/split clips, keyframes, effects, captions, role-based audio mixing, markers, checkpoints and hardware-accelerated export — the whole editing vocabulary, exposed as MCP tools, resources and prompts. Edits land live in the timeline the user is watching, every call is recorded in an Agent panel, and a multi-step batch can be rehearsed against a throwaway project clone (`dry_run`) before it touches anything.

Comprehensive video and audio editing MCP server with advanced operations including trimming, merging, effects, overlays, format conversion, audio processing, YouTube downloads, and smart memory management for chaining operations without intermediate files

AI 3D model generation and post-processing: text/image/multiview-to-3D via Tripo, plus retopology, format conversion (GLB/FBX/OBJ/STL/USDZ), and stylization. Single Go binary, 10 tools, async generation with polling.

Video transcoding (MP4, WebM, ProRes, GIF, MP3) and document conversion (PDF, DOCX, HTML, Markdown, XLSX) for AI agents. Per-job billing, no AWS or FFmpeg setup. `npx -y botverse-mcp`

Source-available, local-first video editor for agents: recordings to a finished film. Cut by transcript, hang b-roll off phrases, score, caption, render and master over OpenTimelineIO, ffmpeg, whisper and MLT, then check the render against the edit it came from. Every tool is also a CLI command, plus a browser workspace with an agent pane.

Using ffmpeg command line to achieve an mcp server, can be very convenient, through the dialogue to achieve the local video search, tailoring, stitching, playback and other functions

[SHAR Production](https://sharprod.com/) AI-hybrid video-production metadata gate: read-only local stdio MCP that validates rights-aware production manifests and returns a releasability result. One tested tool; no API key, network calls, local-file access, or publishing operations. Install from source: `npm install && node server.js`.

Turns an agent-authored storyboard.json into a narrated, captioned product-demo MP4 (TTS voiceover, Whisper-synced captions, auto-zoom) via deterministic Chrome replay and ffmpeg; re-renders itself in CI with no API key, and works on localhost or auth-walled apps. Run with `npx -y github:tandryukha/aidemo#stable mcp`.

Audio AI API for stem separation (vocal, drum, bass, guitar, piano), DME separation (dialogue, music, effects), and AI lyrics sync. 7 tools, 11 models, supports WAV/FLAC/MP3/M4A/MOV/MP4.

Control Adobe After Effects from any MCP client: arbitrary ExtendScript, background rendering, deep comp/layer inspection, and first-class Arabic/RTL & multilingual support (works on AE in any UI language). 47 tools.

An omnimodal AIGC framework that seamlessly converts ComfyUI workflows into MCP tools with zero code, enabling full-modal support for Text, Image, Sound, and Video generation with Chainlit-based web interface.

MCP server for ZapCap API providing video caption and B-roll generation via natural language

Unified AI model API for 130+ models across 18 providers. Browse models, check pricing, create image/video/music/audio tasks, poll results, check balance, and call LLM endpoints. Free catalog tools work without an API key. `npx @runapi.ai/mcp`

Turn your self-hosted Immich photo library into a conversation — natural language search via CLIP, geographic album curation from GPS data, cross-source duplicate detection with perceptual hashing, library health reports, and offline-ready interactive HTML galleries. Claude Code plugin with 21 MCP tools, 11 skills, and 5 slash commands.

Guardrailed video editing for AI agents with 135 MCP tools for FFmpeg editing, captions, audio, effects, Hyperframes, repurposing, resumable workflows, quality gates, and provenance receipts. Includes a Python client and `kino` CLI; runs locally with no required API keys.

Local-first AI media workbench with a Canvas, short-form timeline editor, shared Assets, and 29 MCP tools for agent-controlled projects.

Let AI agents watch videos: word-timestamped transcripts, speaker labels, scenes, chapters and exact-moment search from any video URL or file — fully local, no API keys. `npx klaket-mcp`

Headphone/IEM equalization database with 8,800+ models from AutoEQ. Search by name or sound signature, get parametric EQ settings, compare headphones band-by-band, and browse Harman preference score rankings. Includes automatic sound signature classification (Neutral, Warm, Bright, Dark, V-shaped, etc.).

Let an agent read a YouTube video and cite the exact second. Search one video's transcript for a topic and get back only the matching moments with clickable `?t=` deep links, or analyze the frames — slides, charts, demos and on-screen text that is never spoken aloud. Every citation is checked against a recorded frame or a real transcript segment and dropped if it fails. Hosted Streamable HTTP at `https://vidwords.com/mcp`, token header or OAuth, free tier at [vidwords.com](https://vidwords.com?utm_source=gthb_awesome&utm_medium=code&utm_campaign=awesome-mcp).

Zero-auth hosted server with 22 read-only tools: optimize/convert images (WebP/AVIF/JPEG), paste-ready SVG QR codes, cited [Cleanor Labs](https://cleanor.app) data on device storage capacity and next-gen image-format savings (AVIF/WebP/JPEG XL vs JPEG, HEIC conversion tax), plus 18 deterministic dev utilities LLMs get wrong (hash, HMAC, UUID, base64, JWT decode, JSON, regex, cron, unit & base convert, datetime, URL parse, diff, color, palette, slugify, count, SVG placeholder). No API key or signup; Streamable HTTP at `https://mcp.cleanor.app/mcp`.

Suno AI music generation, lyrics, covers, and vocal extraction via Ace Data Cloud API.

Render, analyze, and verify audio (WAV or FLAC) through a fully offline, deterministic engine. Compose scores as data, render byte-identical PCM, pull loudness, pitch, tempo, key, and structure reports, generate spectrograms, and diff two renders against each other. No ffmpeg, no audio device, just numbers an agent can actually reason about. `cargo install cochlea-mcp`

Render videos from JSON via the iLoveVideoEditor cloud API: motion-design templates, GPU effects, transitions, batch rendering, webhooks. `npx -y @ilovevideoeditor/mcp-server`

Generate presentation PDFs, narrated videos, and MP3 audio from Markdown. Free tier requires no API key or local install — add a URL to your IDE config and start generating. Paid tier adds video, audio, async jobs, and account tools.

Provider-neutral short-form AI video MCP and CLI for agents, with dry-run payload validation and optional live generation through Sora, Veo, xAI and Seedance-style providers.

Zero-dependency browser video editor that AI agents drive through a JSON timeline. MCP tools to add/patch clips, keyframes, transitions, text animations and filters, import media, and analyze a reference video into an edit blueprint (shots, beats, BPM, drop); the open editor UI live-reloads on every change and exports via ffmpeg.

An MCP server to search for (free) stock images and videos from pexels.com.

Read your Clipy screen recordings from any agent: search your library, fetch timestamped transcripts, AI summaries, and key moments with video frames (click markers burned in) as inline images. Read-only, free API key. `npx -y @clipy/mcp`

ComputerVision-based 🪄 sorcery of image recognition and editing tools for AI assistants.

Drive Adobe Premiere Pro from an agent through the Scout panel: transcript search with frame-accurate timecodes, markers, cuts, exports, and 266 ExtendScript tools for effects, transitions, export and project management.

Generate video from a prompt, from an image, or from up to thirty reference images, routed across the field of AI video models (Sora, Veo, Kling, Seedance, Hailuo, Wan and more). Quotes the credit cost before spending it, and refunds a technical failure automatically. Hosted remote server with OAuth, plus an MIT stdio bridge for clients that cannot speak streamable HTTP; requires a Musevate account.

Turn narrated screen recordings (or any local video/audio) into agent-ready data: local Whisper transcript, scene keyframes, OCR, full-text search, and wall-clock anchoring that maps spoken remarks to real timestamps for log correlation. No cloud, no LLM inside. `uvx talkthrough-mcp`.

Scores AI image/video generation prompts (0-100) against 18 models (Veo 3, Sora, Kling, Runway, Seedance, Midjourney, Flux, and more) before you spend a generation credit, then rewrites weak ones. Free, hosted remote MCP + npm/PyPI packages.

Submit media-processing jobs to the Rendobar API and upload local files in one tool call. Transcode, run raw FFmpeg, burn captions, and add watermarks over REST. Free tier.

AI media generation (Flux, Veo, Suno) with cost control. Pre-commit pricing, budget enforcement, reserve-burn-refund billing.

Compose motion-graphics videos from a single JSON document (Clipkit Protocol): 15 tools to author, validate, tweak per element, and preview PNG stills in-chat, plus captions and templated promos; hands the human a free browser editor link, with a deterministic GPU runtime for MP4 renders. Hosted at `https://www.clipkit.dev/mcp` or local `npx @clipkit/mcp-server`.

A MCP server that allows one to examine image metadata like EXIF, XMP, JFIF and GPS. This provides foundation for LLM-powered search and analysis of photo librares and image collections.

One tool surface for music, image, video, and audio generation across Suno, Grok Imagine, Seedance, Kling, Hailuo, Wan, VEO, Ideogram, and GPT Image 2. Generate, edit, upscale, reframe, and master through one API key and one credit pool. First key includes free credits, no card required. `npx -y @aetherwave-studio/mcp`

Convert raster images (PNG/JPG/WEBP/TIFF) to SVG vector format. Single tool, accepts base64 or URL input; runs locally via `uvx image2svg-mcp` or as a Docker HTTP server.

AI podcast editing as a service. Upload raw audio or submit a URL, get back edited episodes with filler words removed, noise reduction, transcripts, show notes, and social clips. Includes webhooks for automation.

Full-resolution vision for LLMs. Tiles large images and captures web pages via Chrome CDP so vision models process every detail without downscaling. Generates interactive HTML tile previews. Supports Claude, OpenAI, Gemini presets with per-model token math and entropy-based tile classification.

Turn a public video link (YouTube, Twitch VOD, Kick VOD, TikTok) into a timestamped transcript, chapters and clip suggestions. Hosted Streamable HTTP at `https://clipcliper.com/mcp`, free tier with no API key.

Self-hosted AI studio exposing its local image, video, music-video and Film Crew generation, upscaling, RAG and code intelligence as MCP tools (default-deny policy; renders queue on your own GPU and are polled by batch id). Ships Agent Skills and a Claude Code plugin.

Deterministic, non-generative image editing for agents: straighten, crop, mask, layer, apply LUTs, strip EXIF/GPS, and encode to WebP/AVIF/JPEG/PNG through declarative transform recipes. Originals are never modified, every result is an immutable revision with full lineage, and the same recipe reproduces byte-identical output on any machine. `npx -y atx-mcp --workspace /path/to/asset-workspace`

MCP server for video analysis — extracts transcripts, key frames, OCR text, and annotated timelines from video URLs. Supports Loom and direct video files (.mp4, .webm). Zero auth required.

Generate AI images, video, voiceovers, avatars and UGC ads through 50+ models via fattly.app

Convert HTML to PDF/PNG/WebP/PPTX slide carousels with 11 themes (LinkedIn, Instagram, pitch decks, infographics). Pixel-perfect Puppeteer rendering, dimension-aware reflow for portrait/landscape, token-efficient JSON mode. `npx slideshot-mcp`.

Chat raw clips into a finished cut.

A MCP server for creating GIFs from your videos.

Agent-native media processing via Transloadit's 86+ Robots: video encoding (HLS, H.264, VP9), image manipulation (resize, watermark, smart crop), document conversion, OCR, speech transcription, and more. Hosted or self-hosted via npx.