What is MCP-AI CLAUDE.md?

A set of Claude Code instructions for a project that provides one MCP interface for generating video, speech, music, and transcriptions. MCP is a standard way for an AI agent to call external tools.

Use it when working on the MCP-AI video-generation project, especially its providers, audio modules, server entry points, or configuration.

It gives the agent project-specific context about the architecture, provider system, authentication, asynchronous video jobs, and local file handling.

How ZenforceTaiji/MCP-AI configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ZenforceTaiji/MCP-AI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ZenforceTaiji/MCP-AI/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ZenforceTaiji/MCP-AI

Made for: Claude Code.

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/instructions/zenforcetaiji/mcp-ai/claude-md/github.svg)](https://agentmods.dev/instructions/zenforcetaiji/mcp-ai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zenforcetaiji/mcp-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/zenforcetaiji/mcp-ai/claude-md/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/instructions/zenforcetaiji/mcp-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/zenforcetaiji/mcp-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 878 This file is loaded in full into every session.

When invoked 878 The same file — it is already loaded in full.

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	$0.00878	$0.00878
Opus 5	$0.00439	$0.00439
Sonnet 5	$0.00176	$0.00176
Haiku 4.5	$0.00088	$0.00088

Measured 11d ago against content hash ff15f7f74af0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

MCP-AI CLAUDE.md 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 11d 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-video-gen

Project Overview

Multi-provider MCP server for AI video, speech, music, and transcription. 7 video providers (including Veo img2vid) + 2 TTS + 2 music + STT under one unified interface.

Architecture

Entry: src/video_gen/__init__.py → server.main() via asyncio
Core: src/video_gen/server.py — 7 MCP tool handlers, provider registry init, download helpers
Video Providers: src/video_gen/providers/ — one file per provider, all implement BaseProvider
Audio: src/video_gen/audio/ — TTS, music, and STT modules

Key Design Decisions

Registry pattern: Providers register at import time via _init_providers(), gated by env var presence
Async two-step: All video APIs are async — generate() returns task_id, query() polls until done
Veo dual auth: API key preferred (?key=), ADC fallback. Env vars read at call time, not import time.
Optional deps: google-auth is in [project.optional-dependencies] under gcp extra. Import wrapped in try/except ImportError.
Local file detection: query_video_status checks if video_url starts with / to skip HTTP download (Veo base64 mode saves locally in query())
img2vid: BaseProvider.generate() accepts optional image_url param. Only VeoProvider uses it; others ignore.
Veo reference image boundary: local files, gs:// URIs, and public HTTP(S) URLs are accepted. Reject localhost, .local, and private/loopback IP-literal URLs; verify TLS; cap local/remote images at 20 MiB.
Lyria is synchronous: Uses :predict (not predictLongRunning), returns audio inline. Response field is bytesBase64Encoded (same as Imagen).
Google TTS requires ADC: Cloud TTS endpoint rejects Vertex AI API keys. Only registered when google.auth.default() succeeds.
STT module is standalone: Not a provider class — just an async transcribe() function called directly from server.py.

Provider Patterns

Video providers follow this structure:

__init__ takes API key(s)
generate(prompt, duration, aspect_ratio, image_url) → VideoResult(task_id, status="processing")
query(task_id) → VideoResult with status and video_url

Read the full file on GitHub · 56 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.

11d ago First seen · 56 lines · 878 tokens per session scan A ff15f7f74af0

Subscribe to this mod's changes

MCP-AI CLAUDE.md is an instructions file published in the GitHub repository ZenforceTaiji/MCP-AI (0 stars, last pushed 1mo ago), licensed MIT. It adds 878 tokens to every session, about $0.0044 per session on Opus 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.

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

MCP-AI: Instructions file for Claude Code