Atlas / MCP servers / matthewdailey / Rime

RimeSAFE

mcp/matthewdailey/rime

MCP server for Rime

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
Unlicense
Stars
27
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.rime.ai)

A Model Context Protocol (MCP) server that provides text-to-speech capabilities using the Rime API. This server downloads audio and plays it using the system's native audio player.

Features

  • Exposes a speak tool that converts text to speech and plays it through system audio
  • Uses Rime's high-quality voice synthesis API

Requirements

  • Node.js 16.x or higher
  • A working audio output device
  • macOS: Uses afplay

There's sample code from Claude for the following that is not tested 🤙✨

  • Windows: Built-in Media.SoundPlayer (PowerShell)
  • Linux: mpg123, mplayer, aplay, or ffplay

MCP Configuration

"ref": {
"command": "npx",
"args": ["rime-mcp"],
"env": {
RIME_API_KEY=your_api_key_here

# Optional configuration
RIME_GUIDANCE=""
RIME_WHO_TO_ADDRESS=""
RIME_WHEN_TO_SPEAK=""
RIME_VOICE="cove" 
}
}

All of the optional env vars are part of the tool definition and are prompts to

All voice options are listed here.

You can get your API key from the Rime Dashboard.

The following environment variables can be used to customize the behavior:

  • RIME_GUIDANCE: The main description of when and how to use the speak tool
  • RIME_WHO_TO_ADDRESS: Who the speech should address (default: "user")
  • RIME_WHEN_TO_SPEAK: When the tool should be used (default: "when asked to speak or when finishing a command")
  • RIME_VOICE: The default voice to use (default: "cove")

Example use cases

[](https://www.youtube.com/watch?v=tYqTACgijxk)

Example 1: Coding agent announcements

"RIME_WHEN_TO_SPEAK": "Always conclude your answers by speaking.",
"RIME_GUIDANCE": "Give a brief overview of the answer. If any files were edited,
Read from source at commit 0e0cc645cbbbOBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add rime-mcp --env RIME_API_KEY=${RIME_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "rime-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "RIME_API_KEY": "${RIME_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
speakreadSpeak text aloud using Rime
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (2 observation(s))
Network
declared (1 observation(s))
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, node-fetch, tmp, ws, @types/node, @types/tmp, @types/ws, concurrently
Why it matters. 12 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 0e0cc645cbbbfull audit observations/trust-audit/mcp-server/matthewdailey__rime.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-080e0cc645cbbbSAFEB89first audit
06

Questions

What is the Rime MCP server?

MCP server for Rime

What tools does Rime expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Rime safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Rime need?

It reads RIME_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Rime run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as rime-mcp at 0.8.0.

How current is this page?

The grade is for one exact copy of the source (0e0cc645cbbb), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement