By Pika-Labs
Generate cinematic branded videos, app teasers, podcast clips, and social media content using Pika's AI video engine. Acts as a creative suite for AI agents, enabling lipsync, dubbing, and multi-shot narratives from URLs or prompts.
Generate cinematic 1080p iOS app teaser videos from real App Store screenshots, with a GPT-image-2 enhancement pass on each selected screen before generation. Output is a beat-driven cinematic teaser built from GPT-enhanced screenshots, ending with the brand logo/icon plus a deterministic `COMING SOON` overlay. Screens sourced from Pika MCP App Store fetch, a live website (auto-captured), user-supplied files, or URLs. Starts by sourcing real screens and brand assets before any generation. Triggers on: app sizzle, app teaser, app promo, iOS app promo video, app video, app product video, coming soon, seedance, motion graphics, make a promo for my app, make a video for [app], gpt enhance promo. NOT for: short-form consumer content like GRWM, vlogs, UGC, or non-app product ads (use content-video); app-sizzle is specifically for iOS app teaser videos sourced from App Store screens or real app UI.
Generate 5–6 App Store screenshots in a given brand's aesthetic from a `brand.md`, raw product screenshots, or a public App Store listing fetched through Pika MCP. Story-driven (hook → value → features → proof → close), splashy, on-brand. Outputs 1290×2796 PNGs ready to drop into App Store Connect. Use when someone wants App Store / store listing assets — including: "make me app store screenshots", "design app store screens for [brand]", "I have a brand.md and screenshots, generate store assets", "screenshot set for app launch", "iOS store screens", "app store creative", "store listing visuals", "splashy app store screens", "app-store-screens".
Viral fake "ESPN behind-home-plate broadcast cutaway" of a user — broadcast-style still + 15s Kling-omni clip with native two-announcer commentary that names the user. Fixed trend: Yankees vs Red Sox ALCS Game 3 at Fenway Park, premium seats, scorebug + chyron with the user's name. Triggers: "make me a behind-home-plate cutaway", "fake MLB broadcast of me", "AI ESPN baseball crowd shot", "viral MLB broadcast trend", "Yankees Red Sox cutaway with me". Needs the user's name + one reference photo.
Build a complete brand identity and guidelines PDF from any input — an idea, an existing website, a list of reference brands, product photos, or "I want to rebrand X". Use when someone wants a brand identity but does NOT need a full commerce launch (no Shopify, no product listings, no social posting). Trigger phrases: "build me a brand", "make me a brand", "design a brand identity", "brand guidelines for [X]", "i want a brand book", "create a brand from scratch", "brand for [idea]", "i want a brand that feels like [X] + [Y]", "rebrand my [thing]", "visual identity for [thing]", "build-a-brand".
All-in-one content director that bundles FOUR format specialists — talking-to-camera, silent POV, dance, and stitch/duet — behind a single front door. Ingests the user's Instagram or TikTok handle, then in Stage 0 asks which KIND of trend they want to make (talking / POV / dance / duet, each explained), recommends a format from their profile when they're unsure, and can present a cross-format sampler menu (~10 real trend cards with links spanning all four formats) so the user picks one card. Once a format (and optionally a specific trend) is locked, it loads the matching format playbook from `formats/<format>.md` and runs that pipeline end-to-end. Triggers — "be my content director" (when the user wants to choose a format), "what kind of trend should I make", "talking vs pov vs dance vs duet", "show me trends across formats", "content director bundle", "content-director".
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Give any AI agent a face, a voice, and a full creative studio.
Image, video, music, editing — one identity, one auth, one bill, across every agent you use.
> /pika:podcast https://pika.art
scraping page (capture_website)...
writing 4-act script (Host A · Host B)...
rendering 4 video acts × ~15s (native multi-shot)...
done.
View video: https://cdn.pika.art/agent/.../podcast-final.mp4
Pika ships as three independent surfaces. Pick one, mix two, or use all three — same Pika Agent identity, same auth, same credit pool across every install.
| Surface | What it gives you | Install mechanism | Works with |
|---|---|---|---|
| MCP | 58 atomic creative tools over HTTP MCP with OAuth | Add https://mcp.pika.me/api/mcp to any MCP-aware client | Claude Code, Cursor, Codex, Claude Desktop, Claude.ai connectors, any custom MCP agent |
| Skills | 9 curated /pika:* workflows + MCP wiring | npx skills add Pika-Labs/Pika-Plugins | Any skill-aware agent — Claude Code, Cursor, Codex, OpenCode, Cline, plus 50+ more auto-detected by vercel-labs/skills |
| Claude plugin | Same 9 skills bundled as a Claude Code-native plugin | claude plugin marketplace add Pika-Labs/Pika-Plugins | Claude Code only (marketplace + /plugin commands) |
These aren't tiers — they're orthogonal mechanisms. A Claude Code user can pick the plugin, the skills, or just the raw MCP. A Cursor user picks skills + MCP. A custom agent picks just MCP.
The lightest install. No skill files written to disk. OAuth handles auth automatically on first tool call. Each client expects a slightly different shape — pick the one for your tool:
Claude Code / Claude Desktop — .mcp.json:
{ "mcpServers": { "pika": { "type": "http", "url": "https://mcp.pika.me/api/mcp" } } }
CLI equivalent: claude mcp add --transport http pika https://mcp.pika.me/api/mcp.
Cursor — ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). Cursor uses bare url, no type field:
{ "mcpServers": { "pika": { "url": "https://mcp.pika.me/api/mcp" } } }
Then cursor-agent mcp login pika.
Codex CLI:
codex mcp add pika --url https://mcp.pika.me/api/mcp
Claude.ai connectors — add the endpoint URL in Settings → Connectors. Any other MCP client — follow your client's docs for the config shape; the endpoint is always https://mcp.pika.me/api/mcp.
vercel-labs/skills detects your installed agents and writes each skill to the right path. Pass --agent <name> to target one agent, --all to install to every detected one.
npx skills add Pika-Labs/Pika-Plugins
Then add the MCP block from §1 to your agent. The skills assume the MCP server is registered as pika.
claude plugin marketplace add Pika-Labs/Pika-Plugins
claude plugin install pika@pika-plugins
Full quit + reopen Claude Code, then run /mcp and authenticate pika. The plugin bundles the same 9 skills as §2 plus the MCP wiring — no separate claude mcp add.
Add this to your repo's .claude/settings.json, commit, and push — cloud sessions auto-install at startup:
{
"extraKnownMarketplaces": {
"pika-plugins": {
"source": { "source": "github", "repo": "Pika-Labs/Pika-Plugins" }
}
},
"enabledPlugins": {
"pika@pika-plugins": true
}
}
mcp.pika.me isn't in the default Trusted allowlist — switch the environment's network access to Full, or use Custom with mcp.pika.me added. (Anthropic network access docs)
One time per install. Inside your agent, run /mcp, find pika, hit Authenticate. Your browser opens to the Pika sign-in page, the token caches locally, the MCP reconnects.
Get a developer key (dk_*) at pika.me/dev and export it before launching your agent:
export MCP_AUTH_TOKEN="dk_..."
claude # or cursor, codex, etc.
npx claudepluginhub pika-labs/pika-plugins --plugin pikaAI video generation — describe what you want, Pexo picks the best model across 10+ engines (Seedance, Kling, Veo, Sora) and returns a finished, multi-shot video with music, subtitles, and transitions. Includes the Pexo agent plus image, audio, director, and model-prompting skills.
Comprehensive Google Vertex AI multimodal mastery for Jeremy - video processing (6+ hours), audio generation, image creation with Gemini 2.0/2.5 and Imagen 4. Marketing campaign automation, content generation, and media asset production.
The creative suite for AI agents — motion graphics, asset generation, and video rendering via Remotion + @oanim/core
Full video production pipeline for Remotion — gives Claude eyes (video analysis), voice (TTS/voiceover), ears (music/SFX), stock footage, AI image/video generation, TikTok captions, 3D content, and more. By Dojo Coding Labs.
AI-powered content generation from your terminal — images, video, music, audio, editing, and social publishing
Create HeyGen avatar videos, personalized video messages, and translated / dubbed videos. Build a persistent digital identity from a photo, generate presenter-led videos with your digital twin, and localize existing videos into 175+ languages with voice cloning and lip-sync.