ElevenLabsSAFE
The official ElevenLabs MCP server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!WARNING] This local MCP server is deprecated in favor of the [ElevenLabs hosted MCP server](https://elevenlabs.io/docs/agents-platform/operate/hosted-mcp). The hosted server is available at https://api.elevenlabs.io/v1/mcp, with nothing to install or run locally. It authenticates with OAuth, so no API keys are copied into your client. See the hosted MCP server documentation to connect from Claude, Cursor, or any other MCP client. This repository is no longer actively maintained.[](https://discord.gg/elevenlabs) [](https://x.com/ElevenLabsDevs) [](https://pypi.org/project/elevenlabs-mcp) [](https://github.com/elevenlabs/elevenlabs-mcp-server/actions/workflows/test.yml)
Official ElevenLabs Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and audio processing APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to generate speech, clone voices, transcribe audio, and more.
6d8f6908b623OBSERVED · 2026-09-24Connect
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 elevenlabs-mcp --env ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY} -- uvx elevenlabs-mcp{
"mcpServers": {
"elevenlabs-mcp": {
"command": "uvx",
"args": [
"elevenlabs-mcp"
],
"env": {
"ELEVENLABS_API_KEY": "${ELEVENLABS_API_KEY}"
}
}
}
}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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.pre-commit-config.yaml
malicious_filename = Path("safe_prefix/../../escape.mp3")audio_bytes = base64.b64decode(preview.audio_base_64)
2. Install `uv` (Python package manager), install with `curl -LsSf https://astral.sh/uv/install.sh | sh` or see the `uv` [repo](https://github.com/astral-sh/uv) for additional install methods.
Gates applied: no_behavioural_pass.
6d8f6908b623full audit observations/trust-audit/mcp-server/elevenlabs__elevenlabs-1.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 |
|---|---|---|---|---|---|
| 2026-09-24 | 6d8f6908b623 | SAFE | B | 89 | first audit |
Questions
What is the ElevenLabs MCP server?
The official ElevenLabs MCP server
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.
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 PyPI as elevenlabs-mcp.
How current is this page?
The grade is for one exact copy of the source (6d8f6908b623), read on 2026-09-24. The repository is watched and re-audited when it changes.