FunASR

Name: FunASR
Author: modelscope

by modelscopeversion 0.1.2i★ –iRuns on your computer

Registry nameio.github.modelscope/funasr-mcp

Install

Overview

Description from the maker (original English)

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Design, images & audio

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

DockerDocker installed

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "funasr": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}

Run this in your terminal

claude mcp add funasr -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "funasr": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "funasr": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account modelscope, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Design, images & audioi

More stars than 0% of the other 2180 servers in this category
Published to the registry more recently than 18% of the other 2180 servers in this category
Basic checks equal to or better than 100% of the other 2180 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is FunASR safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.1.2) reached the registry 3 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.

What can I use instead?

In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Figma Context MCP

by GLips

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

Runs on your computer★ 16,165MITUpdated 5 months ago

Install

Claude Real Video

by HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

Runs on your computer★ 2,284MITUpdated 2 months ago

Install

Figma MCP Server

by figma

Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.

Runs in the cloud★ 2,152Updated 13 months ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

FunASR MCP Server

Model Context Protocol server that gives AI assistants local audio transcription with SenseVoiceSmall by default.

Setup

1. Install dependencies

pip install funasr

2. Optional: run with Docker

The Dockerfile starts the MCP server over stdio and is suitable for MCP directory checks that initialize the server and call tools/list.

docker build -t funasr-mcp examples/mcp_server

docker run --rm -i \ -e FUNASR_DEVICE=cpu \ --mount type=bind,src=/path/to/audio,dst=/audio,readonly \ --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope \ funasr-mcp

Verify the image entrypoint and MCP handshake without downloading a model:

python examples/mcp_server/smoke_test.py funasr-mcp

When submitting this server to MCP directories such as Glama, use this folder as the Docker build context so the container entrypoint runs funasr_mcp.py. The repository root glama.json declares GitHub maintainer ownership for Glama, while the glama.json file in this directory declares the container command and metadata for directory scanners.

Official MCP Registry

The versioned Registry metadata is in server.json. It points to the public GHCR image and asks clients to mount one host audio directory at /audio read-only. The Dockerfile carries the matching OCI ownership label:

Current published release:

LABEL io.modelcontextprotocol.server.name="io.github.modelscope/funasr-mcp"

The release workflow validates the metadata against the official schema, builds the image, performs an MCP initialize and tools/list handshake, pushes the versioned image to GHCR, and publishes server.json through the official mcp-publisher CLI.

To release a new MCP server version:

Update version and the OCI image tag in server.json together.
Merge the change after the MCP validation workflow passes.
Have a modelscope organization Owner push the matching mcp-v tag, for example mcp-v0.1.2.
Approve the protected mcp-registry-publish environment deployment.

The official Registry only grants the io.github.modelscope/* namespace to a GitHub organization Owner. Keep the publish environment restricted to release tags and require a maintainer approval because its OIDC token can publish the organization namespace.

After publication, clients can run the pinned image directly:

docker run --rm -i \

--mount type=bind,src=/path/to/audio,dst=/audio,readonly \ --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope \ ghcr.io/modelscope/funasr-mcp:0.1.2

When using the container, pass tool paths under /audio, such as /audio/meeting.wav.

Glama submission checklist

Use these values when adding the server at https://glama.ai/mcp/servers:

Field	Value
Repository URL	https://github.com/modelscope/FunASR
Docker build context	`examples/mcp_server`
Dockerfile path	`examples/mcp_server/Dockerfile`
Server command	`python /app/funasr_mcp.py`
Expected MCP tool	`transcribe_audio`

After Glama finishes evaluation, verify that the listing or API shows an evaluated quality score before adding it to directory PRs. An HTTP 200 from the listing or badge endpoint alone does not prove that a score has been assigned:

[![modelscope/FunASR MCP server](https://glama.ai/mcp/servers/modelscope/FunASR/badges/score.svg)](https://glama.ai/mcp/servers/modelscope/FunASR)

If the badge endpoint still returns 404, keep the badge out of external directory submissions until the Glama listing is live.

Directory listings

The FunASR MCP server is published in the official Registry and listed on mcp.so:

3. Configure your AI tool

Claude Code (~/.claude.json):

"mcpServers": { "funasr": { "command": "python", "args": ["/path/to/examples/mcp_server/funasr_mcp.py"], "env": {"FUNASR_DEVICE": "cuda"} } } }

Claude Desktop (claude_desktop_config.json):

"mcpServers": { "funasr": { "command": "python", "args": ["/path/to/funasr_mcp.py"], "env": {"FUNASR_DEVICE": "cpu"} } } }

Cursor (Settings → MCP Servers → Add):

Command: python /path/to/funasr_mcp.py
Environment: FUNASR_DEVICE=cuda

Tools

`transcribe_audio`

Transcribe a speech audio file to text.

Parameters:

Name	Type	Required	Description
`audio_path`	string	Yes	Path to audio file (wav, mp3, flac, m4a, ogg)
`language`	string	No	`auto`, `zh`, `yue`, `en`, `ja`, or `ko` (default: `auto`)

Returns: Transcribed text with per-segment timestamps when the model returns them.

Example Usage

Once configured, ask your AI assistant:

"Transcribe the meeting recording at ~/Downloads/meeting.wav"
"What was said in this audio file? /path/to/interview.mp3"
"Convert this voice memo to text: ~/voice_note.m4a"

Environment Variables

Variable	Default	Description
`FUNASR_DEVICE`	`cpu`	Device: `cuda`, `cpu`, or `mps`
`FUNASR_MODEL`	`iic/SenseVoiceSmall`	Model name or local model path passed to `AutoModel`

Features

Five-language transcription — Mandarin, Cantonese, English, Japanese, and Korean
Automatic detection or explicit hints — auto, zh, yue, en, ja, and ko
VAD segmentation — splits longer audio before recognition
Optional segment timestamps — included only when the configured model returns them
Configurable local inference — choose the model and CPU, CUDA, or MPS with environment variables
No API key needed — fully local inference
MIT licensed, privacy-friendly (audio never leaves your machine)

Verified Compatibility

Tool	Status
Claude Code	✅ Tested
Claude Desktop	✅ Compatible
Cursor	✅ Compatible
Windsurf	✅ Compatible
Any MCP client	✅ Standard protocol

FunASR

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Design, images & audioi

Common questions

Alternatives

Figma Context MCP

Claude Real Video

Figma MCP Server

README from the maker

FunASR MCP Server

Setup

1. Install dependencies

2. Optional: run with Docker

Official MCP Registry

Glama submission checklist

Directory listings

3. Configure your AI tool

Tools

transcribe_audio

Example Usage

Environment Variables

Features

Verified Compatibility

`transcribe_audio`