What is STeLA MCP?

STeLA MCP (Model Context Protocol) is a Python implementation of an MCP server that provides secure access to local system operations via a standardized API interface.

What is the purpose of STeLA MCP?

It acts as a bridge between applications and your local system, implementing the Model Context Protocol (MCP) architecture to provide a secure, standardized way for applications to execute commands and perform file operations on a local machine.

What are the key features of STeLA MCP?

Key features include command execution, file operations, directory visualization, working directory support, robust error handling, comprehensive output, simple integration, multi-directory support, security-first design, file search, file edit, type safety, and path validation.

How do I install STeLA MCP?

You can install it via Smithery or manually by cloning the repository, creating a virtual environment, and installing dependencies using pip.

What are the prerequisites for installing STeLA MCP?

Python 3.10 - 3.12, pip or uv package manager, and Pydantic v2.x are required.

How do I configure STeLA MCP?

STeLA MCP can be configured using environment variables such as ALLOWED_DIRS, ALLOWED_DIR, ALLOWED_COMMANDS, ALLOWED_FLAGS, MAX_COMMAND_LENGTH, and COMMAND_TIMEOUT.

What security considerations should I keep in mind when using STeLA MCP?

Run with appropriate permissions, use in trusted environments only, implement additional authorization mechanisms, be cautious about allowed directories, implement path validation, use the most restrictive configuration, regularly review and update allowed commands and directories, validate symlinks, and ensure parent directory checks for file creation operations.

How do I start the STeLA MCP server?

You can start the server using the command uv run python -m src.stella_mcp.server.

How can I use STeLA MCP with Claude Desktop?

You can configure STeLA MCP as a tool in Claude Desktop by providing the path to the Python executable and the argument -m src.stela_mcp.server or by using the binary distribution.

What are the available tools in STeLA MCP?

Available tools include execute_command, change_directory, read_file, read_multiple_files, write_file, edit_file, list_directory, create_directory, move_file, search_files, directory_tree, get_file_info, list_allowed_directories, and show_security_rules.