Enables execution of Python code with pexpect functionality for interactive process control and debugging sessions with command-line tools like LLDB and GDB
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pexpect MCP Serverdebug the demo-buggy program with lldb and show me the backtrace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pexpect-mcp
An MCP (Model Context Protocol) server that provides remote pexpect session control for debugging and process interaction.
Overview
This MCP server enables AI assistants to execute Python code with pexpect functionality, allowing for interactive debugging sessions with tools like LLDB, GDB, and other command-line utilities that require programmatic interaction.
In some sense this is less of a pexpect MCP as one that is just maintaining a stateful Python session.
Related MCP server: Python MCP Sandbox
Installation
Usage
As an MCP Server
Add to your Claude Code configuration:
Tool Usage
The server provides a single tool: pexpect_tool
Parameters:
code(string): Python code to execute with pexpect supporttimeout(optional int): Timeout in seconds (default: 30)
Example Usage:
Demo
The repository includes a demo with a buggy C program (demo-buggy.c) that can
be debugged using LLDB through the pexpect interface. This demonstrates the
server's capability for interactive debugging sessions.
Requirements
Python ≥ 3.12.1
pexpect ≥ 4.9.0
mcp ≥ 1.13.0
License
See LICENSE file for details.