Echokit Server
Open Source Voice Agent Platform
What is Echokit Server?
Echokit Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open source voice agent platform
Open Source Voice Agent Platform
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Open Source Voice Agent Platform
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx echokit-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Echokit Server
EchoKit Server is an open-source voice agent platform written in Rust that implements a full ASR-to-LLM-to-TTS pipeline, enabling real-time voice conversations with AI models on embedded hardware like the ESP32 microcontroller as well as general servers. It integrates with OpenAI-compatible ASR and TTS endpoints, Google Gemini Live, ElevenLabs streaming voices, and MCP servers for tool-calling support. Developers building voice assistants, smart speakers, or embedded AI devices use it as the server-side backend that handles speech recognition, conversation management, and voice synthesis.
Prerequisites
- Rust toolchain (stable, installed via rustup.rs)
- An OpenAI API key or compatible ASR/TTS endpoint (e.g. local Whisper server)
- An LLM endpoint compatible with OpenAI chat completions format
- ESP32 hardware (optional — the server also runs as a standalone voice agent)
- Claude Desktop or another MCP client (if using EchoKit's MCP integration)
Clone the repository
Download the EchoKit Server source code from GitHub.
git clone https://github.com/second-state/echokit_server
cd echokit_serverBuild the server
Compile the Rust project in release mode. For ARM64 systems (e.g. Apple Silicon or Raspberry Pi) enable the fp16 target feature.
cargo build --release
# For ARM64 systems:
# RUSTFLAGS="-C target-feature=+fp16" cargo build --releaseConfigure config.toml
Edit config.toml to set your ASR, LLM, and TTS endpoints and API keys. The file uses OpenAI-compatible endpoint URLs so you can point it at any compatible service.
addr = "0.0.0.0:8080"
hello_wav = "hello.wav"
[asr]
platform = "openai"
url = "https://api.openai.com/v1/audio/transcriptions"
api_key = "sk-your-openai-key"
model = "gpt-4o-mini-transcribe"
lang = "en"
[tts]
platform = "openai"
url = "https://api.openai.com/v1/audio/speech"
model = "gpt-4o-mini-tts"
api_key = "sk-your-openai-key"
voice = "ash"
[llm]
platform = "openai_chat"
url = "https://api.openai.com/v1/chat/completions"
api_key = "sk-your-openai-key"
model = "gpt-4o-mini"
history = 5Run the server
Start the server in the background with debug logging enabled. It listens on port 8080 by default.
export RUST_LOG=debug
nohup target/release/echokit_server &Connect a client and test
Open the EchoKit web interface at https://echokit.dev/chat/, enter your server URL, and press the K0 button on an ESP32 device or use a browser microphone to begin a voice conversation.
Echokit Server Examples
Client configuration
Minimal config.toml for running EchoKit Server with OpenAI endpoints for all three pipeline stages.
{
"mcpServers": {
"echokit-server": {
"command": "npx",
"args": ["echokit-server"]
}
}
}Prompts to try
Voice prompts and interaction patterns supported by EchoKit Server.
- "What is the weather like today?" (spoken via ESP32 or browser mic)
- "Set a timer for 5 minutes" (when MCP tool-calling is configured)
- "Translate this to Spanish: good morning, how are you?"
- "Summarize the news headlines for today"
- "Tell me a short joke"Troubleshooting Echokit Server
Build fails with 'error: linker not found' or missing system dependencies
Install the standard Rust build toolchain with 'rustup toolchain install stable'. On macOS install Xcode command line tools with 'xcode-select --install'. On Linux ensure gcc or clang and libssl-dev are installed.
ASR returns empty transcriptions or the server fails to connect to the OpenAI API
Verify the api_key in config.toml is valid and the url matches the endpoint exactly. For custom or local Whisper servers, ensure the endpoint is reachable from the machine running echokit_server and supports the same request format as the OpenAI transcriptions API.
ESP32 device connects but no audio is captured
Ensure the hello.wav startup prompt exists in the working directory. Check that the ESP32 firmware version matches the server version and that the device's microphone is not muted. The RUST_LOG=debug output will show connection and audio pipeline events.
Frequently Asked Questions about Echokit Server
What is Echokit Server?
Echokit Server is a Model Context Protocol (MCP) server that open source voice agent platform It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Echokit Server?
Follow the installation instructions on the Echokit Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Echokit Server?
Echokit Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Echokit Server free to use?
Yes, Echokit Server is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Echokit Server Alternatives — Similar Communication Servers
Looking for alternatives to Echokit Server? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Echokit Server in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Echokit Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.