Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

FunASR

OCI · GHCR.IO/MODELSCOPE/FUNASR-MCP:0.1.2 · SCANNED AUG 3

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

Available components

oci · ghcr.io/modelscope/funasr-mcp:0.1.2 38
−7 this week 38 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • CVE data not yet available for this package.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency-health data not yet available.Unverified
Provenance & Transparency45
Schema Quality & AI Usability75
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 219 tokens (~219/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

oci · ghcr.io/modelscope/funasr-mcp:0.1.2

# add to Claude Code
claude mcp add modelscope-funasr-mcp -- docker run --rm -i ghcr.io/modelscope/funasr-mcp:0.1.2
# add to Codex CLI
codex mcp add modelscope-funasr-mcp -- docker run --rm -i ghcr.io/modelscope/funasr-mcp:0.1.2
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "modelscope-funasr-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  modelscope-funasr-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/modelscope/funasr-mcp:0.1.2"]
// mcp.json
{
  "mcpServers": {
    "modelscope-funasr-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/modelscope/funasr-mcp:0.1.2"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +3
    • Stability: unverified → 0.20 ▲ functional
  • 31 Jul 26 −10
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 +34
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: excellent functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: fail functional
  • 26 Jul 26 11

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed oci/ghcr.io/modelscope/funasr-mcp:0.1.2

Provenance none

Ecosystem: oci · Outcome: none

Reason: no_attestation

MCP tools — 1 exposed · ~219 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
transcribe_audio ~219

Transcribe one existing local audio file with FunASR and SenseVoiceSmall. Use this tool when the user provides a file path accessible to the MCP server and wants speech converted to text. Do not use it for URLs, live microphone streams, or files that are not mounted into the container. The first call may download and load model weights into the model cache, so it can take longer than later calls. Returns transcript text and, when available, time-aligned segments. Supports automatic or explicit Mandarin, Cantonese, English, Japanese, and Korean recognition with VAD segmentation.

NameTypeReqDescription
audio_pathstringyesExisting local audio file path visible to the MCP server, such as /audio/meeting.wav for the container. URLs and live streams are not accepted. Common WAV, MP3, and FLAC files are supported.
languagestring—Optional language hint. Use auto to detect Mandarin, Cantonese, English, Japanese, or Korean, or provide an explicit code: zh, yue, en, ja, or ko.

No output schema declared.

No examples provided.