About Lilith Shell
Lilith Shell is an experimental MCP server for AI assistants to run local shell commands. It offers a single command tool but is explicitly a prototype with significant security gaps, so it is not suitable for production use.
Key features
- 01Run a supplied shell command
- 02Set an optional working directory
- 03Return exit code, stdout, and stderr
- 04Five-minute command timeout
Use cases
- 01Run local commands through an MCP client
- 02Inspect command output and exit status
- 03Prototype shell-command access for an AI assistant
MCP support
It exposes one MCP tool, `execute_command`, which executes a caller-provided command string and returns its exit code, stdout, and stderr. The README warns that it lacks key security controls and should not be used with sensitive data.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.