"An open-source penetration testing framework" matching MCP servers:

A starter template for building Model Context Protocol (MCP) servers with mcp-framework. It includes an example tool and CLI for adding more tools.

A local MCP server that delegates tasks to a subagent runtime via OpenAI-compatible interfaces, enabling file operations, command execution, and rollback of local file changes.

An MCP server for managing remote SSH servers, enabling AI agents to execute commands, transfer files, and perform deployment operations securely.

Operate packet-radio digipeater nodes from Claude and other MCP clients.

Enables ChatGPT's web interface to operate a real Mac by executing shell commands and reading or writing files over a reverse SSH tunnel, without installing a client or consuming API quota.

Project management CLI + MCP server for AI agents. Register projects once, open them anywhere, sync to S3, auto-init git, and wire into the hasna ecosystem.

An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.

A framework for building Model Context Protocol (MCP) servers using pure Bash scripts, allowing for the creation of tools, resources, and prompts without Node.js or Python runtimes. It provides a complete implementation of the MCP spec compatible with any environment running Bash 3.2+ and jq.

Enables AI agents to manage a Canonical Landscape estate, including inventory, alerts, patching, and script execution, with built-in safety layers to prevent accidental destructive actions.

A Docker-based MCP server that grants AI agents direct access to a comprehensive Kali Linux penetration testing toolkit through an isolated container environment.

A minimal MCP server that exposes Metasploit Framework tools to LLMs via msfrpcd, enabling automated penetration testing and exploitation.

Connects MCP clients to a Kali Linux terminal for executing security tools and commands, enabling AI-assisted penetration testing and CTF solving.

Provides access to Kali Linux security tools through a Docker container, enabling penetration testing and security assessments via MCP-compatible clients.

A server that manages conversation context for LLM interactions, storing recent prompts and providing relevant context for each user via REST API endpoints.

Enables AI agents to interact with real terminal sessions across local and remote hosts, driving multi-turn interactive programs like TUIs, REPLs, and SSH prompts through MCP.

Connects MCP-compatible AI clients and agents to one durable Project Brain plus controlled access to authorized project folders on your own machine. Enables file editing, terminal and Git operations, project intelligence, browser automation, and local MCP server federation, all scoped to explicit workspace grants.

MCP server providing Kali Linux security tools for authorized penetration testing, with tiered tool sets for network scanning, web testing, and more, run via Docker stdio.

MCP server for integrating Metasploit Framework with Claude AI, enabling exploit search, session management, and penetration testing through natural language.

Turns any MCP-capable AI agent into a professional penetration testing platform with 150+ security tools, adaptive async tasks, and crash-proof concurrency.

Enables AI assistants to autonomously execute over 200 open-source penetration testing tools via MCP, including reconnaissance, web exploitation, and brute-forcing, through a unified server architecture with Docker sandboxing for safe execution.