ElevenLabsSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/elevenlabs-mcp-server)
A Model Context Protocol (MCP) server that integrates with ElevenLabs text-to-speech API, featuring both a server component and a sample web-based MCP Client (SvelteKit) for managing voice generation tasks.
Features
- Generate audio from text using ElevenLabs API
- Support for multiple voices and script parts
- SQLite database for persistent history storage
- Sample SvelteKit MCP Client for:
- Simple text-to-speech conversion
- Multi-part script management
- Voice history tracking and playback
- Audio file downloads
Installation
Installing via Smithery
To install ElevenLabs MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install elevenlabs-mcp-server --client claude
Using uvx (recommended)
When using `uvx`, no specific installation is needed.
Add the following configuration to your MCP settings file (e.g., cline_mcp_settings.json for Claude Desktop):
{
"mcpServers": {
"elevenlabs": {
"command": "uvx",
"args": ["elevenlabs-mcp-server"],
"env": {
"ELEVENLABS_API_KEY": "your-api-key",
"ELEVENLABS_VOICE_ID": "your-voice-id",
"ELEVENLABS_MODEL_ID": "eleven_flash_v2",
"ELEVENLABS_STABILITY": "0.5",
"ELEVENLABS_SIMILARITY_BOOST": "0.75",
"ELEVENLABS_STYLE": "0.1",
"ELEVENLABS_OUTPUT_DIR": "output"
}
}
}
}Development Installation
- Clone this repository
- Install dependencies:
uv venv
- Copy
.env.exampleto.envand fill in your ElevenLabs credentials
d68d591887b8OBSERVED · 2026-10-07Connect
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 mcp add web-ui --env ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"web-ui": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ELEVENLABS_API_KEY": "${ELEVENLABS_API_KEY}"
}
}
}
}Exposed tools (6)
5 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_job | destructive | Delete a voiceover job and its associated files |
generate_audio_script | read | |
generate_audio_simple | read | Generate audio from plain text using default voice settings |
get_audio_file | read | Get the audio file content for a specific job |
get_voiceover_history | read | Get voiceover job history. Optionally specify a job ID for a specific job. |
list_voices | read | Get a list of all available ElevenLabs voices with metadata |
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
delete_job
const binaryString = atob(result.audioData.data);
@modelcontextprotocol/sdk, @sveltejs/adapter-auto, @sveltejs/kit, @sveltejs/vite-plugin-svelte, svelte, svelte-check, typescript, vite
load_dotenv() # load environment variables from .env
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
d68d591887b8full audit observations/trust-audit/mcp-server/mamertofabian__elevenlabs.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | d68d591887b8 | SAFE | B | 89 | first audit |
Questions
What tools does ElevenLabs expose?
6 in total: 5 read-only, 0 that write, and 1 that can delete or overwrite (delete_job). Every one is listed on this page with its risk.
Is ElevenLabs 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. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does ElevenLabs need?
It reads ELEVENLABS_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 ElevenLabs run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as web-ui at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (d68d591887b8), read on 2026-10-07. The repository is watched and re-audited when it changes.