Offense
Security tools for coding agents: dependency advisory audits and evidence for remediation.
Open the source (opens github.com) https://github.com/offense-research/offense
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from io.github.offense-research.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://offense.sh/mcp
From the server's entry in the official MCP Registry
Related
-
AgentHound
MCP serversOffensive 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.
git clone https://github.com/adithyan-ak/AgentHound.git -
LitterBox
MCP serversA self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
git clone https://github.com/BlackSnufkin/LitterBox.git -
The Quiet Protocol Growth Offense MCP
MCP serversRead-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
-
blitzstrike
MCP serversBlitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.
git clone https://github.com/shinthink/blitzstrike.git -
pentest-ai
MCP serversOpen-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
git clone https://github.com/0xSteph/pentest-ai.git -
o360-mcp
MCP serversRun Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes
o360-mcp@1.0.2