GLaDOS MCP Server
A Model Context Protocol server that provides GLaDOS-style voice commentary for AI development workflows, along with professional Kokoro TTS voices.
Overview
This project combines:
- GLaDOS Voice: Authentic Portal-style audio synthesis with characteristic commentary
- Professional Alternatives: 26 Kokoro voices for serious development work
- MCP Integration: Seamless integration with existing Model Context Protocol tools
Demo Videos (Turn on sound)
https://github.com/user-attachments/assets/f5623dd5-ac9b-4adc-8641-104d634504c7
https://github.com/user-attachments/assets/542fb5c6-03ab-4f4d-9e73-0d7f29a71c4e
Installation
1. Download Models (Required)
python download_models.py
2. Install System Dependencies
Linux (Ubuntu/Debian):
sudo apt update
sudo apt install portaudio19-dev python3-pyaudio
Linux (Fedora/RHEL):
sudo dnf install portaudio-devel python3-pyaudio
macOS:
brew install portaudio
3. Install the Server
cd glados-mcp
python -m venv venv
source venv/bin/activate # Windows users: venv\Scripts\activate
pip install -e .
Configuration
Add this to your MCP client configuration:
{
"mcpServers": {
"glados-mcp": {
"command": "./glados-mcp/venv/bin/python",
"args": ["-m", "tts.server"],
"cwd": "./glados-mcp",
"env": {
"PYTHONPATH": "./glados-mcp",
"MCP_DEBUG": "1",
"MCP_LOG_LEVEL": "DEBUG"
}
}
}
}
Note: Make sure the paths match your actual installation directory. If you installed in a different location, adjust the command and cwd paths accordingly.
Usage
The interface is straightforward:
Default GLaDOS Voice:
speak("Your code is... adequate. I suppose.")
Professional Kokoro Voices:
speak("Analysis complete.", voice="af_alloy")
speak("Task finished.", voice="bm_daniel")
Available Voices:
list_voices() # Returns all 26 Kokoro voices plus GLaDOS
Voice Options
- GLaDOS (default): Characteristic Portal-style commentary
- Kokoro Female US: af_alloy, af_aoede, af_bella, af_jessica, af_kore, af_nicole, af_nova, af_river, af_sarah, af_sky
- Kokoro Female British: bf_alice, bf_emma, bf_isabella, bf_lily
- Kokoro Male US: am_adam, am_echo, am_eric, am_fenrir, am_liam, am_michael, am_onyx, am_puck
- Kokoro Male British: bm_daniel, bm_fable, bm_george, bm_lewis
Project Structure
├── download_models.py # Downloads TTS models (run this first!)
├── mcp.json # MCP client configuration
├── glados-mcp/ # Main server code
│ ├── tts/ # TTS system
│ ├── models/ # Voice models (downloaded by script)
│ └── README.md # Detailed instructions
Requirements
- Python 3.10+
- Audio output
- Internet connection for model download
- Linux: PortAudio system library (
portaudio19-dev)
License
Apache 2.0
"The cake is a lie, but the voice commentary is real."
Metadata
Release files for iflow-mcp_halfaipg-glados-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_halfaipg_glados_mcp-0.1.0.tar.gz | 6.5 MB | Without provenance | Details for iflow_mcp_halfaipg_glados_mcp-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_halfaipg_glados_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_halfaipg_glados_mcp-0.1.0-py3-none-any.whl |
Total release size: 6.5 MB
Release files / iflow_mcp_halfaipg_glados_mcp-0.1.0.tar.gz
| Download URL | iflow_mcp_halfaipg_glados_mcp-0.1.0.tar.gz |
|---|---|
| Size | 6.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5d916efba9da10f0c87b6631a0d905c05509674f62d2cf46ca8ca3fc66157103
|
|
BLAKE2b-256 checksum How to use checksums |
1b90c8e5f7151f40b38a6cf76b87c91e2e493dfc61d9480da41b1c7cdcfe0122
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_halfaipg_glados_mcp-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_halfaipg_glados_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 31.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f975df79d14f5b0ff76465eebaccc2a353205b700aace366fcf8a59f554456a9
|
|
BLAKE2b-256 checksum How to use checksums |
42dce1bf0bc327b4bf0907d7cf8358595d49600a6f6da5421692e22e3a9fcfb2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_halfaipg-glados-mcp 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.