AgentHound
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for
Install
go install github.com/.../agenthound@latest Maintain this server? Add the badge
Show your README readers it's in a curated directory — and give them a one-click path to install docs and config.
← links back here Markdown
[](https://prismix.dev/mcp/adithyan-ak-agenthound) Theme-aware version (auto dark/light on GitHub) →
<a href="https://prismix.dev/mcp/adithyan-ak-agenthound"><picture><source media="(prefers-color-scheme: dark)" srcset="https://prismix.dev/api/badge/mcp/adithyan-ak-agenthound.svg?theme=dark"><img alt="Listed on Prismix" src="https://prismix.dev/api/badge/mcp/adithyan-ak-agenthound.svg"></picture></a> About
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for
More AI servers
-
Brave Search
Web + local-business search via the Brave Search API — privacy-first, no Google account required.
-
Memory
Knowledge-graph memory — store entities, observations, and relations across conversations.
-
Sequential Thinking
Structured chain-of-thought scaffolding — the model writes its own multi-step plan as MCP calls.
Discussion (0)
Sign in to comment →No comments yet. Sign in to start the discussion.