agentsploit is an open-source CLI framework designed for offensive security testing of AI agents and Model Context Protocol (MCP) servers. It provides tools for prompt injection, red teaming, and agent security research, supporting security professionals and developers.
agentsploit is a Penetration testing & red teaming project. It focuses on testing and securing AI agents and MCP servers against offensive security threats. It is built as an open-source project for AI security researchers, red teamers, developers of AI agents. The project is open source (Apache-2.0). agentsploit is available on the command line, and it can be self-hosted.
agentsploit first shipped in 2026. The project is developed in the open on GitHub with 24 commits in the last 90 days. Key capabilities include prompt injection testing, red teaming, and MCP server support. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do