By jcodesmore
Discover, recommend, and track movies in Claude Code. TMDB-powered via moviedb-promise, with a taste profile and watch history that follow you across projects.
npx claudepluginhub jcodesmore/jcodesmore-plugins --plugin movies-for-ai-agentsFirst-run configuration for the movies-for-ai-agents plugin. Use when the user says "set up movies-for-ai-agents", "configure movies", "first run", "add my TMDB key", "set up my movie profile", or when any other movies-for-ai-agents skill calls an MCP tool that reports "TMDB API key not configured". Captures the TMDB API key and, optionally, a brief taste-priming pass (favorite genres, directors, a few favorite movies) so later recommendations work out of the gate.
Browse what's popular, trending, newly released, currently in theaters, or filter by IMDb rating / interest / director. Use when the user asks "what's popular right now", "what's trending", "what's new", "what's in theaters", "show me this week's movies", "anything good out lately", "sci-fi with IMDb 8+", "heist movies", "Nolan films", "hidden gems", or wants to see a feed of current hot titles. Not for personalized picks — for that, use `recommend`. Not for finding a specific title — for that, use `find-movie`.
Search for a specific movie by title, keyword, year, or fuzzy description. Use when the user asks "find that movie…", "what's the name of the movie where…", "search for [title]", "look up [title]", "tell me about [movie]", or wants information about a specific film they already have in mind. Not for open-ended recommendations — for that, use the `recommend` skill.
Silently keep the user's watched history and taste profile current as they mention movies in conversation. Use whenever the user says "I watched X", "I saw X last night", "I just finished X", "we watched X", "loved X", "hated X", "didn't like X", "that was great/terrible", "best movie ever", "worst movie", "add X to my watchlist", or otherwise signals a movie-viewing event or taste reaction — even if it's a passing mention in the middle of another topic. Do NOT trigger on hypotheticals ("I want to watch X", "I should watch X") — those belong on the watchlist instead. This skill exists so the user's taste profile and history stay rich without any manual logging.
Personalized movie recommendations tailored to the user's stored taste profile, watch history, and whatever mood/constraint they mention right now. Use when the user asks "what should I watch", "recommend me a movie", "suggest something", "I'm in the mood for [X]", "something like [X]", "help me pick a movie", "got two hours tonight — what should I watch", "anything I'd like that's new", or any other open-ended ask for a personalized pick. This is the flagship skill — invest in making each recommendation feel reasoned, not generic.
Ask "what should I watch tonight?" and get picks that actually fit your taste. Mention a film and Claude quietly logs it. The more you talk, the smarter it gets.
Quick Start · Try it · Discord
Click to watch — 40-second demo.
1. Get a free TMDB API key (~2 minutes) at https://www.themoviedb.org/settings/api — copy your API key.
2. Install the plugin — inside Claude Code, run:
/plugin marketplace add JCodesMore/jcodesmore-plugins
/plugin install movies-for-ai-agents@jcodesmore-plugins
Then fully restart Claude Code (quit the app and reopen).
3. Add your key — run /movies-for-ai-agents:setup and paste it when prompted. Done.
Talk to Claude like a friend:
Tell Claude you'll watch something tonight, and next session it'll ask how it went. Your taste profile follows you across every project and every machine.
Discord — chat, help, show-and-tell · Issues — bugs & feature requests · Contribute · More plugins
Everything stays on your machine, outside any one project folder:
~/.claude/data/movies-for-ai-agents/
├── config.json ← your TMDB API key (permissions 600)
├── preferences.json ← your taste profile (liked genres, directors, interests, etc.)
├── watched.json ← what you've seen
├── lists.json ← every custom list, including the default "watchlist"
├── active.json ← films you've started but not finished
├── imdb-cache.json ← cached imdbapi.dev responses (24h/6h TTLs)
└── imdb-interests.json ← cached IMDb interest taxonomy (7d TTL)
Your taste follows you across every project and every machine that shares this directory. No telemetry, no analytics — nothing leaves your machine except TMDB search queries.
| Something's off | Fix |
|---|---|
| "TMDB API key not configured" | Run /movies-for-ai-agents:setup — or set TMDB_API_KEY in your shell environment. |
Plugin doesn't show up in /mcp | Fully quit Claude Code and reopen. The plugin registers on startup. |
| "Cannot find module '@modelcontextprotocol/sdk'" | Only happens with manual install — run cd mcp-server && npm install. |
| Recommendations still feel generic | Tell Claude about 3–5 movies you love. Give it some signal to work with. |
More help in the Discord.
If you'd rather clone and run it directly:
git clone https://github.com/JCodesMore/movies-for-ai-agents.git
cd movies-for-ai-agents/mcp-server && npm install
cd ..
claude --plugin-dir .
Or skip /movies-for-ai-agents:setup entirely by exporting your key as an environment variable:
export TMDB_API_KEY="your_key_here"
The environment variable takes precedence over config.json when both are set.
Requirements: Node.js ≥ 18, free TMDB API key.
Apache License 2.0 — © 2026 JCodesMore
This product uses the TMDB API but is not endorsed or certified by TMDB.
Part of jcodesmore-plugins.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub
Excalidraw diagramming toolkit — auto-diagram any codebase, architecture diagrams, data flows, with PNG/SVG/URL export
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains