AgentHound

MCP serverGitHubActiveGo

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 the agentic stack.

Description provenance: Original source

Open canonical source

Measured: Oct 20, 2026 · 65 observations

Domains & Uses

Domains: Agents, skills and MCP

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/adithyan-ak/AgentHound

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

453stars · Oct 20, 2026

+13 (+3 %)since Sep 22, 2026

Exact values · 29 readings

Measured	stars	Change
Oct 20, 2026	453	0
Oct 19, 2026	453	0
Oct 18, 2026	453	+1
Oct 17, 2026	452	+1
Oct 16, 2026	451	+1
Oct 15, 2026	450	-1
Oct 14, 2026	451	+2
Oct 13, 2026	449	+2
Oct 12, 2026	447	0
Oct 11, 2026	447	0
Oct 10, 2026	447	+1
Oct 9, 2026	446	+1
Oct 8, 2026	445	0
Oct 7, 2026	445	+3
Oct 6, 2026	442	0
Oct 5, 2026	442	-1
Oct 4, 2026	443	0
Oct 3, 2026	443	0
Oct 2, 2026	443	+1
Oct 1, 2026	442	0
Sep 30, 2026	442	+1
Sep 29, 2026	441	0
Sep 28, 2026	441	+1
Sep 27, 2026	440	+1
Sep 26, 2026	439	+1
Sep 25, 2026	438	-2
Sep 24, 2026	440	0
Sep 23, 2026	440	0
Sep 22, 2026	440	·