FunASR
FunASR is an MCP server that gives AI assistants local audio transcription with SenseVoiceSmall by default. The Dockerfile starts the MCP server over stdio and is suitable for MCP directory checks that initialize the server and call tools/list. It has 21,043 GitHub stars, is released under the MIT license and runs locally with docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2.
github.com/modelscope/FunASR (opens in a new tab)
Data as of from the GitHub API and the official MCP registry; description from the project's repository. Report an error
Install FunASR
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"funasr": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio funasr -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2Cursor
{
"mcpServers": {
"funasr": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"funasr": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
Tools (3)
Parsed from the Tools section of the README; check the repository for the current list.
transcribe_audioTranscribe a speech audio file to text.
audio_pathstring
languagestring
About FunASR
Model Context Protocol server that gives AI assistants local audio transcription with SenseVoiceSmall by default. The Dockerfile starts the MCP server over stdio and is suitable for MCP directory checks that initialize the server and call tools/list.
- pytorch
- speech-recognition
- paraformer
- punctuation
- speaker-diarization
- voice-activity-detection
- asr
- multilingual-asr
- speech-to-text
- transcription
Similar MCP servers
More ai & search MCP servers
Context7
upstash/context7
Context7 Platform -- Up-to-date docs for AI agents.
Active · last commit Nov 14, 2026
AI & searchTypeScriptHoncho
plastic-labs/honcho
Memory that reasons: continual learning for stateful agents.
Active · last commit Nov 12, 2026
AI & searchPythonWARM
writerslogic/warm
Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.
Active · last commit Nov 16, 2026
OfficialAI & searchRustSui Knowledge Base (kapa.ai)
MystenLabs/sui
Semantic search across Sui documentation and knowledge sources, powered by kapa.ai.
Active · last commit Nov 14, 2026
AI & searchRustFidelis Memory
hermes-labs-ai/fidelis
Recall locally stored agent memories through an MCP-compatible host.
Active · last commit Oct 19, 2026
OfficialAI & searchPythonSemble
MinishLab/semble
Fast and Accurate Code Search for Agents.
Active · last commit Nov 8, 2026
AI & searchPython
How do I install the FunASR MCP server?
Add the command docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2 to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is FunASR free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is FunASR actively maintained?
The most recent commit was on Nov 15, 2026. The latest release is v1.4.26, published Nov 12, 2026. appsgit only lists MCP servers with a commit in the last six months.