MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for KiVio creators — upload AI-generated videos, manage series, respond to │ │ Description │ commissions, earn 70% of every coin parents spend. The first MCP built for AI-video │ │ │ creator monetization.
npm -
Local-first production desk for solo creators: six AI pipelines (video, novel, podcast, course, writing, shorts), approval-gated agents, versioned files, MCP + A2A. The Windows installer bundles its own runtime.
MIT -
Local-first production desk for solo creators: six AI pipelines (video, novel, podcast, course, writing, shorts), approval-gated agents, versioned files, MCP + A2A. The Windows installer bundles its own runtime.
MIT ★ 1 -
Local-first production desk for solo creators: six AI pipelines (video, novel, podcast, course, writing, shorts), approval-gated agents, versioned files, MCP + A2A. The Windows installer bundles its own runtime.
MIT -
clipwise-mcpgithub.com/mobileshop9991-star/clipwise-mcpupdated this year
MCP server for Clipwise — AI tools for short-form video creators (TikTok, Reels, Shorts)
npm MIT ★ 1 -
Give your AI agent a social media brain: TikTok, YouTube Shorts & Instagram Reels trends, viral video analysis, creators, sounds & hashtags. MCP server + skills for Claude Code, Cursor, Codex.
MIT ★ 4 -
soorafr-mcpgithub.com/rocnubie/soorafr-mcpupdated this year
Soora FR is a French-language platform for AI video generation, giving francophone creators direct access to a suite of modern video models — including Sora 2, Kling, Veo, Seedance, PixVerse, and Runway — through a single interface.
MIT -
TikTok Integration Serverno update data
Enable your applications to analyze TikTok videos for virality factors, retrieve video content and subtitles, and interact conversationally with TikTok videos. Access detailed metadata about TikTok posts including creator info, hashtags, and engagement metrics. Seamlessly integrate TikTok data into AI workflows to enhance content understanding and interaction.
smithery -
TikTok API for developers and AI agents: video search, comments, creator profiles and followers, hashtag videos, Creative Center ads, TikTok Shop, transcripts. One key, pay per call, no login. Python, curl and MCP examples. TikTok 数据接口。
MIT -
Local-first video editor for AI agents and creators. 57 MCP tools: auto-edit, shorts, captions, music, QC. Footage never leaves your PC.
npm MIT ★ 3 -
digestrgithub.com/aronreisx/digestrupdated this year
An AI-powered daily digest creator that transforms YouTube videos into high-fidelity audio news programs using Gemini summarization and pluggable TTS backends (Gemini & Kokoro). supports CLI, FastAPI, and MCP.
-
YouTube Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_trainability`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
Turn a song into a music video on one Apple Silicon Mac. Beat-synced cuts, local AI for every shot, and an AI agent (Claude Code / Codex via MCP) that can run the whole edit.
MIT -
commercial-creatorgithub.com/cxbxmxcx/commercial-creatorupdated this year
Agentic AI commercial pipeline: product description in, finished video ad out. Claude agents plan + QC, Seedance 2.0 generates, ElevenLabs voices and scores. FastAPI + web UI + MCP connector for Claude Code.
MIT ★ 6 -
Agent-native AI video studio for Claude, Codex & DeepSeek. Create from ideas or repurpose long-form media with MCP, FFmpeg, and local-first workflows.
MIT ★ 1 -
Kabo: your creator partner inside Claude, ChatGPT, Grok Bot and Muse. Remake a viral video with you on camera, right from your phone, plus daily picks, account reviews and scripts for YouTube, Instagram and TikTok.
npm MIT ★ 2 -
Agent-first short-form AI video generation CLI and MCP server for Sora, Veo, xAI and Seedance
npm MIT ★ 3 -
Sovereign creator substrate: one BYOK MCP engine (image/video/audio/taste/ledger/publishing) that brand packs build on. MIT.
MIT -
Mapflyover — turn any place on Earth into a cinematic 3D map flyover video. AI narration, captions and cinematic camera moves. Connects to Claude & ChatGPT.
★ 1 -
viral-finder-mcpupdated this year
MCP server for Viral Finder - AI-powered video analysis for YouTube, TikTok, and Instagram
npm MIT -
ClipForge(原『带货剪手』/ daihuo-jianshou):开源 AI 带货短视频神器——上传一张商品图,AI 自动提炼卖点 + 写种草脚本 + 锁定商品原图不变形 + 配画面/配音/字幕,一键产出抖音小店 / 快手 / 小红书 / TikTok Shop 卖货短视频。0 成本批量出片、开源无水印、本地自部署。也支持一句话主题成片。Open-source AI e-commerce/UGC short-video generator.
AGPL-3.0 ★ 1,298 -
@spycy/mcpactive
Model Context Protocol server for Intentos: research creators, analyze and remix videos, keep a vault of hooks, generate images and video, and manage Meta campaigns from Claude, Cursor and other MCP clients.
npm MIT -
@renzo.johnson/youtube-mcpactive
YouTube MCP server for Claude Code, Cursor, Copilot and five more AI agents. mcprush.com-a6fb3e5ae8910debf0fd1d15
npm MIT -
Upload, Update or Schedule videos on Youtube with the help of AI
go MIT ★ 68 -
boqo, the autonomous AI agent for social media, for Claude Code: find videos, make captioned vertical clips, schedule and auto-post to TikTok, Instagram and YouTube. Plugin + remote MCP server.
MIT ★ 2 -
Free remote MCP server: transcribe, read and download public Reels, TikToks and YouTube videos, plus sourced creator data. https://shortformkit.com/mcp
MIT -
Instagram Edits for Mac + Claude Code: plugin and MCP server that gives Claude the full 274-tool editor. Let Claude edit your Reels: beat cuts, captions, transitions, export.
pypi MIT ★ 18 -
tubelens-ossgithub.com/mbettan/tubelens-ossupdated this year
Open-source FastMCP server for deep YouTube video intelligence and creator research using Google Gemini with zero local downloads.
Apache-2.0 -
Public quickstart for Tukey's remote MCP server: evidence-backed video and Reel ideas for a creator's own connected YouTube channel or confirmed public Instagram account, in Claude (Connectors Directory) or ChatGPT (custom app).
★ 1 -
youtube-mcpgithub.com/miller-joe/youtube-mcpupdated this year
OAuth-authenticated YouTube MCP for channel owners. Edit videos, reply to and moderate comments, query analytics, and set AI thumbnails via a ComfyUI bridge.
npm MIT ★ 1 -
Trovegithub.com/antoinebecker10-afk/Troveupdated this year
🦞 Your content. All of it. Semantic search across GitHub, files, screenshots, videos — one index, one search bar. MCP server for Claude Code.
MIT ★ 2 -
klamdo-mcpgithub.com/klamdo-app/klamdo-mcpupdated this year
MCP server for Klamdo — connect your AI agent via MCP or REST API. Generate identity-locked 4K images, video, scripts, voiceover, and full content packages as typed deliverables.
npm -
After Effects-style motion graphics for code and AI agents — keyframes, text animators, kinetic typography, MCP server. From the creator of CustomerPro.in.
NOASSERTION -
Make my clips look like that video. Zing studies a video you like and cuts your clips into captioned drafts in that style, in 16:9, square and 9:16, and makes memes from local photos. Pre-alpha local CLI and MCP server; installs from source with Python, uv and FFmpeg.
MIT -
YouTube connector for search volume over time, and for the videos trending on YouTube right now. Add it to Claude, ChatGPT or Cursor in one click (MCP). Free plan.
MIT -
MCP server and Claude Code plugin: characters whose every trait grows from one story — then concept art, scene, video, voice and music. For film, games, ads and books.
npm MIT ★ 1 -
Open-source 2D skeletal animation editor for games and film. AutoRig layered PSDs, animate with meshes, IK and physics, lip-sync from audio, render video, export JSON/.skel. JavaScript, Rust, Godot and Unity runtimes. Built-in MCP server for AI assistants. Docs: rigby2d.com/docs
Apache-2.0 ★ 272 -
Official Spyglass plugin for Claude: search brands, creators, Meta ads, Instagram posts, TikTok videos, hooks, campaigns, landing pages, and public comments.
MIT