VideoGenerationMCP
An MCP server for video generation using Kling Omni and Seedance 2 via PiAPI, with ElevenLabs voiceovers and Hebrew BVAC lipsync, featuring local validation before API calls.
README
VideoGenerationMCP
A FastMCP server that gives agents a validated interface to Kling Omni + Seedance 2 video generation (via PiAPI) and ElevenLabs voiceover — with every provider constraint enforced locally (Pydantic) before any paid API call.
Tools
| Tool | Purpose |
|---|---|
generate_kling_video |
Kling Omni single- or multi-shot generation |
generate_seedance_video |
Seedance 2 generation; auto-chains the Hebrew BVAC lipsync pipeline |
generate_seedance_first_last |
Seedance first/last-frame interpolation |
generate_elevenlabs_voiceover |
ElevenLabs TTS with character-level timestamps |
transliterate_hebrew |
Hebrew → Latin (LLM-backed) for lipsync prompts |
list_voices |
List ElevenLabs voices |
get_task |
Poll any PiAPI task |
upload_asset · list_assets · get_asset · delete_asset |
PiAPI private asset library (reusable asset:// persona refs) |
Highlights: Hebrew BVAC lipsync (ElevenLabs eleven_v3 → ffmpeg black-video carrier →
Seedance omni_reference) with two Scribe audio gates; @-tag reference validation;
a content gate (blocks minor/real-person prompts); private-asset support on the
less-restriction tier; 720p default (1080p on request).
Requirements
- Python ≥ 3.12 and
uv ffmpegon PATH (brew install ffmpeg/apt install ffmpeg)PIAPI_KEYandELEVENLABS_KEY(see.env.example)- Optional:
OPENROUTER_API_KEY(fallback for Hebrew transliteration; primary is a local LMStudio model, defaultgoogle/gemma-4-e4b)
Setup
git clone git@github.com:AvivK5498/VideoGenerationMCP.git
cd VideoGenerationMCP
uv sync
cp .env.example .env # fill in PIAPI_KEY + ELEVENLABS_KEY
uv run pytest -q # 203 tests
Run standalone (stdio): uv run python -m video_mcp.server
Connect to Claude Code
claude mcp add video \
--env PIAPI_KEY=your_piapi_key \
--env ELEVENLABS_KEY=your_elevenlabs_key \
--env OPENROUTER_API_KEY=your_openrouter_key \
-- uv run --directory /ABSOLUTE/PATH/TO/VideoGenerationMCP python -m video_mcp.server
Or add it to a project .mcp.json:
{
"mcpServers": {
"video": {
"command": "uv",
"args": ["run", "--directory", "/ABSOLUTE/PATH/TO/VideoGenerationMCP", "python", "-m", "video_mcp.server"],
"env": { "PIAPI_KEY": "…", "ELEVENLABS_KEY": "…", "OPENROUTER_API_KEY": "…" }
}
}
}
Verify with /mcp inside Claude Code.
Connect to Codex
Add to ~/.codex/config.toml:
[mcp_servers.video]
command = "uv"
args = ["run", "--directory", "/ABSOLUTE/PATH/TO/VideoGenerationMCP", "python", "-m", "video_mcp.server"]
env = { PIAPI_KEY = "…", ELEVENLABS_KEY = "…", OPENROUTER_API_KEY = "…" }
(or codex mcp add video -- uv run --directory /ABSOLUTE/PATH/TO/VideoGenerationMCP python -m video_mcp.server).
Codex MCP servers communicate over stdio; restart Codex to pick up the config.
More
CONTRACT.md— full interface spec for every module.samples/payloads.md— ready-to-use tool-call examples.scripts/— live end-to-end drivers used to validate against PiAPI/ElevenLabs.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.