Media · Local MCP server
FunASR
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.modelscope/funasr-mcp- Version
- 0.1.2
- Status
- Active
- Category
- media
- Transport
- stdio (local process)
- Package
- OCI image (Docker)
- Published
- 2026-07-26
- Updated
- 2026-07-26
- Publisher
- modelscope (GitHub)
- Website
- github.com/modelscope/FunASR/tree/main/examples/mcp_server
- Repository
- github.com/modelscope/FunASR (folder examples/mcp_server)
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| OCI image (Docker)runtime: docker | ghcr.io/modelscope/funasr-mcp:0.1.2 | — | stdio |
How to connect FunASR
FunASR runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/modelscope/funasr-mcp:0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"funasr-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More media servers
| Server | Runs |
|---|---|
| Freebeat MCPFreebeat MCP server for AI music videos, effects, and media uploads. | Local · stdio |
| Freetogame MCPBrowse free to play PC games and their details from FreeToGame. No key required. | Local · stdio |
| FreeTTSText to speech in 149 languages: MP3 links from any assistant. Free without an account. | Remote & Local · HTTP, stdio |
| FrenchieOCR, transcription, file extraction, and image generation for AI agents via MCP. | Remote & Local · HTTP, stdio |
| Fundamentals MCPUnofficial read-only MCP for fundamentals, macro & news (EDGAR + FRED + Tavily, BYO-key). | Local · stdio |
| Furlen MCPTurn a CSV or a named public dataset into an animated chart video, figures re-checked first. | Local · stdio |
| Future Video StudioCreate and manage cinematic AI video renders through the Future Video Studio Agent API. | Remote & Local · HTTP, stdio |
| FXI StudioGenerate cinematic images and video and chain shots into continuous motion. | Remote · HTTP |