A remote MCP server for creating video advertisements through Prizmad's UGC video studio. UGC means user-generated-content-style video, and MCP lets compatible AI applications connect to external tools.

Use it from an MCP-compatible application to connect to Prizmad and create video ads.

It lets supported AI clients drive the video-making service programmatically, using OAuth sign-in or an API key.

mcp-server — Skill for Claude Code and Codex by prizmad/agent-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add prizmad/agent-skills --skill mcp-server

Clone the repo

git clone --depth 1 https://github.com/prizmad/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/prizmad/agent-skills/mcp-server/github.svg)](https://agentmods.dev/skills/prizmad/agent-skills/mcp-server)

Your own site

<a href="https://agentmods.dev/skills/prizmad/agent-skills/mcp-server"><img src="https://agentmods.dev/badge/skills/prizmad/agent-skills/mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/prizmad/agent-skills/mcp-server"><img src="https://agentmods.dev/badge/skills/prizmad/agent-skills/mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,056 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.02056
Opus 5.5	$0.00024	$0.00822
Sonnet 5.5	$0.00012	$0.00411
Haiku 4.5	$0.00006	$0.00206

Measured 2mo ago against content hash 638a768006ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mcp-server/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prizmad MCP Server

Prizmad exposes a remote Model Context Protocol (MCP) server. Any MCP-compatible host (Claude Desktop, Claude.ai web, ChatGPT, Cursor, Continue, Zed, Claude Code CLI, n8n, custom SDKs) connects and drives the full UGC video studio programmatically.

Endpoint: https://prizmad.com/api/mcp
Transport: streamable-http
Server card: https://prizmad.com/.well-known/mcp/server-card.json
Source code (stdio bridge for stdio-only clients): https://github.com/prizmad/Prizmad-MCP-server

Connect (primary path — OAuth Connect button)

Modern MCP clients click Add custom connector → enter the MCP URL and the OAuth flow runs automatically:

Client probes https://prizmad.com/api/mcp → 401 with WWW-Authenticate: Bearer resource_metadata="…".
Client reads /.well-known/oauth-protected-resource and /.well-known/oauth-authorization-server.
Client POST /oauth/register (RFC 7591 Dynamic Client Registration) — no manual app pre-registration needed.
Browser opens https://prizmad.com/oauth/authorize → user signs in (NextAuth) → consent screen → redirect back with code.
Client exchanges code for an RS256 JWT (audience https://prizmad.com/api/mcp).
Client calls https://prizmad.com/api/mcp with Authorization: Bearer <jwt>. Refresh tokens rotate; PKCE S256 mandatory.

Compatible clients: Claude Desktop, Claude.ai, ChatGPT, Cursor, Zed, Claude Code CLI. Same-origin design (authorize/token/register all live on prizmad.com) sidesteps the Claude.ai web bug that ignores cross-origin authorization endpoints.

Streamable HTTP config (when manual config is needed)

{
  "mcpServers": {
    "prizmad": {
      "transport": "streamable-http",
      "url": "https://prizmad.com/api/mcp"
    }
  }
}

The Connect flow handles the Bearer token automatically. To pre-fill an existing API key instead, add "headers": { "Authorization": "Bearer przmad_sk_live_..." }.

stdio-only clients (via the published bridge)

Read the full file on GitHub · 160 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 160 lines · 60 tokens per session scan A 638a768006ea

Subscribe to this mod's changes

mcp-server is a skill published in the GitHub repository prizmad/agent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 60 tokens to every session and 2,056 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media Marketing and SEO agent-skills ai-agents ai-video anthropic claude marketing

ads-performance-analytics

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…

rampstackco/claude-skills · 147 tokens

ads-creative-development

How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns…

rampstackco/claude-skills · 124 tokens

paid-media-strategy

A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…

rampstackco/claude-skills · 142 tokens

create-short

Create a short-form vertical video (TikTok, Instagram Reels, YouTube Shorts). Optimized 9:16 pipeline with a live Studio preview, auto-captions, hook-first structure, and background music mood selection; renders to MP4 only when you ask.

DojoCodingLabs/remotion-superpowers · 58 tokens

create-video

Full video production pipeline — from a text prompt to a live Studio preview with voiceover, music, sound effects, stock footage, and motion graphics, rendered to MP4 when you ask. The flagship command of Remotion Superpowers.

DojoCodingLabs/remotion-superpowers · 50 tokens

review-video

Review a Remotion video with AI vision. Starts with a cheap local check of rendered still frames, then has TwelveLabs watch the full render and score it against a JSON rubric (pacing, composition, text legibility, audio sync and more) with timestamped fixes, applies the fixes and re-reviews. The feedback loop that…

DojoCodingLabs/remotion-superpowers · 75 tokens