Moltis
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
What is Moltis?
Moltis is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to secure persistent personal agent server in rust. one binary, sandboxed execution, multi-provider llms, voice, memory, telegram, whatsapp, discord, teams, and mcp tools. secure by design, runs on your ...
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A secure persistent personal agent server in Rust. One binar
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx moltisConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Moltis
Moltis is a secure, self-hosted personal AI agent server written in Rust that runs as a single binary on your own hardware. It connects to multiple LLM providers (OpenAI, Anthropic, local models, and more) and exposes those capabilities through messaging platforms including Telegram, Signal, Microsoft Teams, Discord, and a built-in web UI. Developers and privacy-conscious users choose Moltis because it keeps all data on-premise, supports voice with 8 TTS and 7 STT providers, and integrates with MCP servers via both stdio and HTTP/SSE transports, all behind vault encryption and passkey authentication.
Prerequisites
- macOS, Linux, or a Docker-capable host with internet access
- An API key for at least one LLM provider (e.g., Anthropic, OpenAI, or a local Ollama instance)
- Docker or Podman if you want sandboxed code execution
- An MCP-compatible client (Claude Desktop, Claude Code, or any MCP host) to connect to Moltis as an MCP server
Install Moltis
Install the Moltis binary using the one-line script on macOS or Linux. Homebrew and Docker images are also available.
curl -fsSL https://www.moltis.org/install.sh | shRun the first-time setup wizard
Launch Moltis to start the interactive setup. It will print a setup code to the terminal; visit the local web UI and enter the code to complete initial configuration including choosing your LLM provider and setting an authentication password.
moltisConfigure environment variables for unattended deployment
For Docker or CI deployments, set the required environment variables before starting the container so Moltis boots without interactive prompts.
export MOLTIS_PASSWORD=your-strong-password
export MOLTIS_PROVIDER=anthropic
export MOLTIS_API_KEY=sk-ant-...Run Moltis via Docker
Pull and start the official Docker image. Mount the config volume and expose the Docker socket to allow sandboxed tool execution.
docker run -d --name moltis -p 13131:13131 \
-e MOLTIS_PASSWORD=your-strong-password \
-e MOLTIS_PROVIDER=anthropic \
-e MOLTIS_API_KEY=sk-ant-... \
-v moltis-config:/home/moltis/.config/moltis \
-v /var/run/docker.sock:/var/run/docker.sock \
ghcr.io/moltis-org/moltis:latestConnect to the web UI
Open your browser and navigate to the Moltis web UI. Use the password you configured to log in and start chatting with the agent.
open https://localhost:13131Add Moltis as an MCP server in Claude Desktop
Moltis exposes an MCP-compatible HTTP/SSE endpoint. Add it to your Claude Desktop configuration so Claude can delegate tasks to it.
{
"mcpServers": {
"moltis": {
"command": "moltis",
"args": ["--mcp"]
}
}
}Moltis Examples
Client configuration
Add Moltis to Claude Desktop by running it directly as an MCP server subprocess.
{
"mcpServers": {
"moltis": {
"command": "moltis",
"args": ["--mcp"],
"env": {
"MOLTIS_PROVIDER": "anthropic",
"MOLTIS_API_KEY": "sk-ant-..."
}
}
}
}Prompts to try
Sample prompts you can use once connected to Moltis through an MCP client.
- "Remember that my preferred coding language is TypeScript and always suggest TypeScript solutions."
- "Search my conversation history for anything I said about the Q4 budget."
- "Send a Telegram message to my team that the deployment is done."
- "Run the script at /home/user/scripts/backup.sh in a sandbox and show me the output."Troubleshooting Moltis
Browser shows a TLS certificate warning when visiting https://localhost:13131
Moltis uses a self-signed certificate by default. Accept the browser warning for local use, or pass --no-tls if you are running behind a reverse proxy that handles TLS.
Moltis cannot execute sandboxed tools
Ensure the Docker socket is mounted (-v /var/run/docker.sock:/var/run/docker.sock) or that Podman is available on the host PATH. Without a container runtime, sandboxed execution is disabled.
LLM API calls fail with authentication errors
Verify that MOLTIS_API_KEY matches the provider set in MOLTIS_PROVIDER. For Anthropic the key starts with sk-ant-; for OpenAI it starts with sk-. Restart Moltis after changing environment variables.
Frequently Asked Questions about Moltis
What is Moltis?
Moltis is a Model Context Protocol (MCP) server that secure persistent personal agent server in rust. one binary, sandboxed execution, multi-provider llms, voice, memory, telegram, whatsapp, discord, teams, and mcp tools. secure by design, runs on your hardware. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Moltis?
Follow the installation instructions on the Moltis GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Moltis?
Moltis works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Moltis free to use?
Yes, Moltis is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Moltis Alternatives — Similar Coding Agents Servers
Looking for alternatives to Moltis? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Moltis 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 Moltis?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.