Pexpect
This MCP server provides remote process control and debugging capabilities through Python's pexpect library, enabling AI assistants to spawn, interact with, and control command-line programs, debuggers, and interactive shells. Built by Mitsuhiko using FastMCP with timeout handling and session persistence, it executes Python code that can launch processes like lldb, gdb, or any terminal application, then send commands and capture output through expect patterns. The implementation maintains global session state across tool calls and includes a demo buggy C program for testing debugging workflows, making it valuable for automated debugging sessions, system administration tasks, and scenarios where AI assistants need to interact with command-line tools that require real-time input/output control.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/mitsuhiko/pexpect-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Pexpect from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.