
fitv-mcp
io.github.hanshs474/fitv-mcp
Make video clips with sound from a prompt or a photo on freeimagetovideo.ai, on your own API key.
Documentation
Free Image to Video MCP server
Free image to video AI with no daily cap: start with no sign-up, keep going on a free account. Every video comes with sound and no watermark. This is the official MCP server for Free Image to Video: Claude, Cursor, Cline, Windsurf or any MCP client can turn a prompt or a photo into a video clip on your own account and hand back the file URL.
- Pass a prompt for free text to video AI, or a public photo URL as
image_urlto animate a photo with it as the first frame. - Every clip is image to video AI with sound: the soundtrack is made in the same pass, on MiniMax H3.
Tools
| Tool | What it does |
|---|---|
generate_video | Text to video, or photo to video with image_url. Returns a run id |
check_status | Status of a run, and the video URL when it is ready |
credits | Credits left on your account (free to call) |
generate_video takes prompt (required), image_url, duration (4, 5, 6, 8, 10 or 15 seconds), resolution (480p default, 768p), aspect_ratio (16:9 default, 9:16, 1:1) and model (minimax-h3, the only one).
API key and plan
Create a key at freeimagetovideo.ai/settings/apikeys and set it as FREEIMAGETOVIDEO_API_KEY. API runs need a paid plan: each run draws on the plan's daily full-speed allowance, then waits in the relaxed queue (pricing). To make clips without a key, use the generator on the website.
Install (local, stdio)
npx -y freeimagetovideo-mcp
Claude Desktop / Cursor / Cline / Windsurf
{
"mcpServers": {
"freeimagetovideo": {
"command": "npx",
"args": ["-y", "freeimagetovideo-mcp"],
"env": { "FREEIMAGETOVIDEO_API_KEY": "sk-..." }
}
}
}
Claude Code in one line:
claude mcp add freeimagetovideo -e FREEIMAGETOVIDEO_API_KEY=sk-... -- npx -y freeimagetovideo-mcp
Remote (Streamable HTTP, no install)
https://freeimagetovideo.ai/api/mcp
Hosted on freeimagetovideo.ai itself, with the same three tools. Send your key with each request as Authorization: Bearer sk-...; listing the tools needs no key.
claude mcp add --transport http freeimagetovideo https://freeimagetovideo.ai/api/mcp --header "Authorization: Bearer sk-..."
{
"mcpServers": {
"freeimagetovideo": {
"url": "https://freeimagetovideo.ai/api/mcp",
"headers": { "Authorization": "Bearer sk-..." }
}
}
}
Server Card: https://freeimagetovideo.ai/.well-known/mcp/server-card.json
Gemini CLI
gemini extensions install https://github.com/hanshs474/fitv-mcp
Notes
- Video takes minutes.
generate_videoreturns a run id; poll it withcheck_status. - Refusals say what to do next: a bad key, a plan that does not include API runs, too many runs at once, or a prompt the content filter refused.
- No dependencies: plain
fetchand JSON-RPC over stdio, Node 18 or newer. FREEIMAGETOVIDEO_BASE_URLoverrides the endpoint; only useful for testing.
MIT licensed. Made by Free Image to Video.
freeimagetovideo-mcpnpm install freeimagetovideo-mcpRemote
Related Servers
io.github.hanshs474/aigifmaker-mcp
MCP server for AI GIF Maker (aigifmaker.ai): turn text into animated GIFs from any MCP client.
io.github.hanshs474/movoa-mcp
Movoa (movoa.ai), the AI video generator with sound: text and photo to video from any MCP client.
io.github.hanshs474/seedance-prompts-mcp
Search, audit and compose AI video prompts — 150 of them, each rendered into a real video