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. 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.
-
gemini-creative-plugingithub.com/2901were/gemini-creative-pluginupdated this year
Gemini Creative — Claude Code plugin wrapping a Model Context Protocol server for AI image generation via Google's Gemini 3 image models. Sessions-first API with 9 auto-activating skills for game art, UI mockups, character sprites, and prompt engineering.
MIT ★ 1 -
MCP server for TikTok Symphony Creative Studio: Claude Code and Claude Desktop drive trend templates, reference-to-video, avatars, try-on, video refresh, dubbing and the editor through the SymFlow Chrome extension — on your own Symphony account and weekly
npm MIT -
AI creative studio for Windows. Connect your favorite AI through MCP and direct videos, ads, designs and music from your chat, or paste your own key and create with no code. No membership, with free options included.
GPL-3.0 -
google-labs-claudegithub.com/holm-digital-io/google-labs-claudeupdated this year
Claude Code plugin and MCP server that connects Google Labs creative tools to Claude: Veo video generation, Stitch UI design, and Pomelli brand content — all three generating against one shared brand identity.
MIT ★ 1 -
System health auditor for AI-powered development machines. Ten Gate scoring maps machine metrics to creative capacity. CLI + MCP server + Claude Code plugin. By Arcanea.
MIT -
cell-memgithub.com/Aether-liusiqi/cell-memupdated this year
Brain-inspired memory system for AI agents. Four memory layers (working, episodic, semantic, procedural) with consolidation, self-reflection, generative replay, and creative hypothesis discovery. Ships as an MCP server for Claude Code & Codex CLI.
MIT ★ 1 -
Fashion E-Commerce Intelligencegithub.com/alexgenovese/ecommerce-fashion-market-analysisno update data
# Fashion E-Commerce Intelligence MCP Server Empower your AI agents, copilots, and assistants with vertical domain-specific fashion intelligence. Built by [alexgenovese.com](https://alexgenovese.com), this Model Context Protocol (MCP) server provides automated **SEO auditing, category trend research, DTC demand forecasting, CRM segment enrichment, and campaign creative generation**—designed natively for Cursor, Claude Desktop, Claude Code, and any MCP-compatible environment. --- ## ⚡ What It Does | Capability | Without this server | With Fashion MCP | |---|---|---| | **SEO Auditing** | Manual checklists, generic advice | Automated **0-100 score** across 5 dimensions with fashion-specific validation (fit, material, color, season, schema, OG, Twitter Cards). | | **Trend Research** | Generic search queries | Deep category-level trend intelligence (trending keywords, colors, silhouettes, price tiers, market fit, confidence). | | **Demand Forecasting** | Spreadsheets & gut feel | Explainable weighted-rule forecast model: `baseline × trend × media × retention × inventory × seasonality` with backtesting. | | **CRM Segment Enrichment** | Static email lists | Customer segments enriched with trending colors/silhouettes/keywords, audience clusters, and ready-to-send targeted messaging. | | **Campaign Creative** | Standard copywriters per channel | Platform-specific campaign themes, hooks, value propositions, and ready-to-use creative briefs grounded in real-time trend data. | --- ## 🔧 Exposed Tools - `product_seo_audit`: Audit any fashion product listing for SEO best practices, structured schema, meta tags, and fashion relevance (fit, size, material). - `fashion_trend_analysis`: Analyze fashion trend data mapped from search engine and social media queries. *(Receives search data input seamlessly, no API key required)*. - `fashion_category_demand_outlook`: Get a rapid, light demand pulse check for a specific product category in a target market and season. - `fashion_dtc_forecast_analysis`: Generate complete DTC demand forecasts with scenario planning (base/upside/downside) and stock-out/overstock risk analysis. - `fashion_customer_trend_enrichment`: Map trending keywords, colors, and silhouettes onto existing CRM customer segments for targeted email/SMS campaigns. - `fashion_campaign_theme_recommendation`: Recommend conversion-optimized ad campaign themes, hooks, and creative briefs for Meta, Google, TikTok, or Email. --- ## 🔐 Privacy & Technical Features - **No API Keys Required:** All analysis, SEO audits, demand forecasts, and CRM enrichment tools run locally with the data you supply. Upstream search data for `fashion_trend_analysis` uses your existing Tavily MCP server. - **Explainable Outputs:** Every tool returns explicit `assumptions[]`, `dataGaps[]`, and `confidence` scores, so your agent always understands the reasoning behind recommendations. - **Zero-Config Local Cache:** Uses a local SQLite persistence layer (`~/.fashion-mcp/store.db`) to cache snapshots, feature stores, and forecast actuals for backtesting. ## 💻 Local Installation To install this stdio-based server locally via Smithery: ```bash npx smithery install alexgenovese/ecommerce-fashion-market-analysis ```
smithery -
PrivacyScrubber PII Masking MCPno update data
Zero-Trust Data Sanitization (ZTDS) MCP Server for Claude Desktop, Cursor, Windsurf, and other AI clients. Automatically intercepts and redacts PII, credentials, and sensitive corporate data locally on your machine before they are sent to external LLMs. ### 🔒 100% Local & Airplane Mode Verified All sanitization runs inside local RAM. No data ever leaves your computer, ensuring compliance with GDPR, HIPAA, SOC 2, and internal GRC policies. Zero network calls, zero server logs. ### 🛠️ Supported Formats & File Types Locally parse and sanitize: - **Documents:** `.docx` (Microsoft Word) parsed locally with Zero-Server extraction. - **Code & Configs:** `.js`, `.py`, `.go`, `.rs`, `.json`, `.yaml`, `.ini`, `.env`, and source code files. - **Data & Logs:** `.txt`, `.log`, `.csv`, `.tsv`, `.md`, and plain text outputs. ### 🏷️ Redacted Entity Types - **Personal Data:** Names (`NAME`), Emails (`EMAIL`), Phone Numbers (`PHONE`). - **Credentials:** API Keys, passwords, tokens, SSH keys, database URIs. - **Identifiers (`ID`):** SSNs, Tax IDs, credit card numbers, and custom regex patterns. ### 🎛️ 22+ Specialized Industry Detection Profiles Specify detection rules tailored to your workload (requires PRO key): - **Engineering & IT:** `Dev`, `Tech`, `Security`, `Agents` - **Corporate & Operations:** `General`, `Bizops`, `Sales`, `Support`, `Marketing`, `Creative` - **Financial & Professional:** `Finance`, `WealthMgmt`, `Insurance`, `Accounting` - **Legal & Compliance:** `Legal`, `Compliance`, `CCPA`, `HR` - **Healthcare & Research:** `Medical`, `Pharma`, `Academic` - **Personal Use:** `Personal` ### 🔧 Available Tools - `sanitize_text` — Scrub PII/Secrets locally in text context. - `reveal_text` — Reversible token mapping (Original -> Token -> Original). - `sanitize_file` — Local sanitization of raw plain text and DOCX files.
smithery -
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 -
Claude Code plugin: create images and translate text into Emirati (UAE) Arabic, powered by the Antigravity CLI
MIT -
大瑀创意科技 AI Skill — MCP 营销服务查询 | AI Marketing Service Skill by DY Creative&Tech (Hangzhou) — MCP Server for Douyin, Xiaohongshu, AIGC marketing
MIT ★ 1 -
muse-mcpgithub.com/rishi-golla/muse-mcpupdated this year
Creativity Layer for AI Agents
MIT ★ 2 -
Meta ads for AI agents: find the ads that pay, run creative tests and launch the next one paused. Plugin and remote MCP server for Claude, ChatGPT, Codex, Cursor, Gemini CLI and Grok.
MIT -
Built for the It's Today Media $5,000 Build Challenge. AI creative strategy engine for affiliate media buyers — mines winning competitor ads, deconstructs their creative DNA, audits your ad set for Entity ID collapse, and generates net-new angle briefs with platform-ready copy.
-
Hannagithub.com/JosephOIbrahim/Hannaupdated this year
Always-on AI producer that surfaces decisions across a creative portfolio. Producer-rhythm twin cloned from Harlo's cognitive substrate. Family-first by design.
Apache-2.0 ★ 2 -
App Store & Google Play screenshot generator: free web editor, MCP server and CLI. iPhone Duo, Creative Assets, exact-size exports.
MIT ★ 1 -
Remote MCP server for AdMakeAI (https://admakeai.com/api/mcp): design ad creatives and copy, make UGC video ads, research competitors' Meta Ad Library ads, and draft and report on Meta campaigns
MIT -
Lets your AI drive a live generative art studio: read the canvas, move knobs, switch engines. MCP server.
MIT -
@damagethundercat/puredata-mcpgithub.com/damagethundercat/puredata-mcpupdated this year
A TypeScript MCP server for launching, controlling, and live-patching Pure Data.
npm MIT -
Dependency-free WebGL studio for generative backgrounds and live embeds.
MIT ★ 95 -
Open-source 2D animation editor. Create with Claude Code or Codex via MCP, then refine layers and keyframes visually.
MIT ★ 8 -
TDPilot — local TouchDesigner AI copilot with 114 MCP tools, native atomic transactions, verified rollback, MCP SDK 2, grounded planning, and live validation.
MIT ★ 17 -
PureData-MCPgithub.com/damagethundercat/PureData-MCPupdated this year
Control and live-patch Pure Data from AI agents via MCP
MIT ★ 2 -
SlopCamera lets your coding agent make images, diagrams, animation, 3D scenes, and video from source files it can keep revising.
npm MIT -
touchdesigner-mcpgithub.com/aliphi/touchdesigner-mcpupdated this year
MCP server for TouchDesigner — let Claude (and any MCP client) create operators, set parameters, and wire networks inside a running TouchDesigner project via a Web Server DAT.
MIT -
Free images for AI agents: openly-licensed CC images & audio with attribution via NPX
npm MIT -
nano-banana-mcpgithub.com/seungmanchoi/nano-banana-mcpupdated this year
MCP server for AI image generation and editing powered by Google Gemini
npm ★ 4 -
Creative-direction lens reconstructed from 125 public records of Min Hee-jin's work (interviews, talks, credits): 32 principles, each traced to sources. MCP server + single-file guide for ChatGPT, Claude, Codex. Independent research; not affiliated with or endorsed by Min Hee-jin or ooak records.
NOASSERTION -
The Infinite audiovisual engine as an MCP server for Claude Desktop, Cursor and Windsurf. Free and open source.
npm MIT -
The complete end-to-end frontend engineering and design orchestrator for AI agents and developers. 16 pillars, MCP server, 3D WebGL, typography, motion, and automated QA.
MIT ★ 2 -
td-universal-toolkitgithub.com/kalektika/td-universal-toolkitupdated this year
Unified MCP toolkit for TouchDesigner - gives any AI agent live network control, 630-operator knowledge base, and a closed visual feedback loop
MIT ★ 1 -
MCP server for Suno AI music generation. Create, manage, and iterate on AI music directly from Claude Code, Cursor, or any MCP client.
MIT ★ 2 -
Real-time character-grid image renderer for macOS — GUI + CLI + MCP server. p5.js + Tauri 2 + Rust.
MIT ★ 1 -
Claude Code plugin + MCP server for SoundCloud: find tracks artists made free to download, check licenses, and build DJ sets ordered by BPM and Camelot key. Metadata & links only, no ripping.
MIT ★ 1 -
touch-mcpgithub.com/benoitliard/touch-mcpupdated this year
High-performance MCP server for TouchDesigner — live control via WebSocket with 29 tools (nodes, parameters, connections, CHOP/TOP/SOP/DAT data, timeline, render, layout, batch). Python + FastMCP
★ 5 -
@dpantani/tdmcpgithub.com/pantani/tdmcpupdated this year
tdmcp — the TouchDesigner MCP server. Build real TouchDesigner visual systems from plain language with Claude, Cursor, or Codex (Model Context Protocol).
npm MIT -
Local-first AI media generation and video editing toolkit for coding agents, with a Bun CLI, TypeScript SDK, MCP server, and Agent Skill.
npm MIT -
PostScript for precision and imagination. A modern PostScript interpreter in Rust for precise document rendering and expressive generative art. PNG, SVG, PDF, WASM, and MCP.
npm Apache-2.0 ★ 2 -
Image search MCP server for AI agents: 1.85M openly licensed images with source, license and attribution. Claude plugin + remote MCP at lightdrift.ai/mcp
-
Local-first TouchDesigner AI copilot with 114 MCP tools, truthful concept routing, deterministic visual techniques, transactional execution, live validation, and rollback.
npm MIT -
The programmable era of ads. Video made in code for experts and their AI agents: a film is render(t). Determinism checks, H.264/ProRes rendering, review and per-placement delivery, with an MCP server and agent skills.
MIT ★ 7 -
Make funky shader loops, posters, FastSD images and 9:16 product video ads with Claude, on your own computer. One MCP server + Claude Code plugin. No cloud, no accounts, no NVIDIA GPU.
MIT ★ 1 -
Key-free MCP servers that let LLMs build real TouchDesigner networks: local knowledge base (no API keys), offline .toe/.tox generation, live TD editing. Eval-gated - 636/636 build-token-exact.
AGPL-3.0 ★ 1 -
Give your AI agent a video ad studio. It decodes a winning ad shot by shot, then edits 9:16 ads from your own footage: captions, voice-over, deterministic ffmpeg render and QC. MCP server for Claude Code, Codex, Cursor.
MIT ★ 1 -
Open-source, local alternative to Higgsfield on the kie.ai API: 25 video/image/avatar/audio models, approve-before-you-spend storyboards, plus a CLI, MCP server and Claude Code skills.
MIT -
Galta: an AI infinite canvas and moodboard beside the web page you're browsing. Collect references with their sources, draw, point and ask; Codex or Claude Code works on the canvas. Local-first.
AGPL-3.0 ★ 2 -
An atomised index of TouchDesigner, a live bridge into a running instance, and an offline .toe reader — exposed to AI agents over MCP.
MIT -
firefly-services-mcpgithub.com/Focus-GTS/firefly-services-mcpupdated this year
Model Context Protocol server for Adobe Firefly Services — exposes Firefly, Photoshop API, and Lightroom API endpoints as MCP tools for Claude Code, Cursor, and other MCP clients. Built by FocusGTS.
Apache-2.0 ★ 1 -
月瑀科技 AI Skill — MCP 账号营销服务查询(小红书 / 达人投放 / 信息流广告 / 线索转化 / 营销复盘)| AI Marketing Skill by YUEYU TECH (Hangzhou) — MCP Server for account marketing, Xiaohongshu influencer placement, feed ads & lead conversion
MIT ★ 3 -
A Linux DJ studio and DAW that a human and an AI agent play together over MCP. Arrangement with mixer and automation, a modular synthesizer with synths, drums and effects, VST3/LV2 hosting, stem separation, live coding, warp. Public beta.
AGPL-3.0 ★ 1 -
紙に描いた絵コンテを撮ると、字幕入りの9:16動画になって返ってくる。依存ゼロ・ブラウザ完結のY2K/グリッチ系 画像&ショート動画スタジオ。WebGL2 + Cloudflare Workers。 / Photograph a storyboard you drew on paper, get a captioned 9:16 video back. Dependency-free, runs entirely in your browser.
MIT ★ 2 -
MCP server and Claude Code plugin for photo to TikTok, Instagram Reels, YouTube Shorts, and Facebook video. Upload 1–10 photos, get a captioned reel. 27 MCP tools + 4 skills + 3 slash commands. $0.06 base render, 50 free seeds, no subscription. Built for SMBs.
MIT -
Render HTML canvas animations to MP4 fast on a Mac, with WebCodecs hardware H.264 in headless Chrome (8.4 min 1080p60 in 161 s instead of 426 s). MCP server for Claude Code, Codex and Cursor. Ships 66 code-made film styles from LemoLab's lemo-opuscar. Free for non-commercial use.
npm NOASSERTION ★ 7 -
Connect Milanote to Claude Code, ChatGPT, Cursor and any AI agent. Milanote MCP server, no API key from Milanote needed.
NOASSERTION -
TouchDesigner MCP server, describe a visual to Claude, Cursor or Codex and it builds a real, playable node network (audio-reactive, generative, particle, 3D, feedback) with live knobs + MIDI/OSC/DMX, then checks for errors and previews its own work.
npm MIT ★ 62 -
Click any mesh in a three.js or React Three Fiber scene to see the line of code that made it, the calls that led there and the helpers it used, then edit its values live. A Vite plugin with one-command setup and nothing to add to your code, plus an MCP server for AI assistants like Claude Code.
npm MIT ★ 1 -
MCP server for LinkedIn Campaign Manager - ad account, campaign, ad set, and creative management via Claude
MIT -
@productmaker/mcpactive
ProductMaker MCP server — cost products, generate landing pages, UGC videos, and ad creatives, and publish to Shopify, Meta Ads, and TikTok Ads.
npm MIT -
Claude plugin for Proxy: Meta, Google, LinkedIn and TikTok ad-library access, competitor research, creative strategy and ad scripts. No API keys.
MIT -
Claude MCP for TikTok Symphony Creative Studio: trend templates, reference-to-video, avatars, try-on, video refresh, dubbing and the editor through the SymFlow Chrome extension
MIT