FunASR is an open-source toolkit for recognizing speech from audio, including offline, streaming, and edge deployments, with components for voice activity detection, punctuation, and speaker processing. Developers use it to build transcription and audio-analysis pipelines, including services compatible with OpenAI APIs. The catalogue MCP add-on gives coding agents a way to work with FunASR.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/modelscope/funasr/mcp_server-funasr-mcpgit clone --depth 1 https://github.com/modelscope/FunASRWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/modelscope/funasr/mcp_server-funasr-mcp)<a href="https://agentmods.dev/mcp/modelscope/funasr/mcp_server-funasr-mcp"><img src="https://agentmods.dev/badge/mcp/modelscope/funasr/mcp_server-funasr-mcp.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
funasr-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"funasr-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2",
"type=bind,src={audio_directory},dst=/audio,readonly",
"type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope"
],
"env": {}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 14 lines scan A 237975910322
funasr-mcp is an MCP server published in the GitHub repository modelscope/FunASR (20,173 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
neuronscope
CLI and MCP server for tracing which neurons and attention heads drive a language model's output, built on TransformerLens. Runs locally from the neuronscope-cli Python package.
traintools
Agent-ready, paper-backed PyTorch training diagnostics for gradients, batches, data quality, plasticity, and stopping. Runs locally from the traintools Python package.
health-system-profiler
MCP server "health-system-profiler" as configured in ajhcs/healthcare-data-mcp. Launched with hc-mcp health-system-profiler.
openfoodfacts-mcp-server
Barcode lookup, nutrition search, and product comparison for 3M+ crowd-sourced food products. Runs locally from the @cyanheads/openfoodfacts-mcp-server npm package. Needs 5 environment variables to run.
clinical-trials-ai-mcp
MCP server for clinical trials ai. Features search trials, check eligibility, get trial details. From MEOK AI Labs. Runs locally from the clinical-trials-ai-mcp Python package.
ensembl
Ensembl REST — vertebrate genomes, sequences, comparative genomics, variation. Remote server at gateway.pipeworx.io.