1. Conduid
  2. Agents
  3. Invaris Agentsec
MCP server · Agents

Invaris Agentsec

by · github.com/invarislabs/invaris-agentsec

Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.

Unclaimed adversarial-testingagent-securityai-agentsai-securitydevsecopsgithub-actionslangchainllm-securitymcpmodel-context-protocolowaspprompt-injectionpytestpythonred-teamingsecurity-testing
InstallView source
34Low

Scored 20 days ago · breakdown

About Invaris Agentsec

Invaris Agentsec is an MCP server published by invarislabs in the Agents category: adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.

The repository has 2 stars and 0 forks, with the last commit 6 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/invarislabs/invaris-agentsec

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Invaris Agentsec

Powered by Claude · Grounded in docs

I know everything about Invaris Agentsec. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.9.0AgentSec 0.9.0 · 12 Oct 2026New: `agentsec dashboard`, a local, read-only web dashboard over the report files AgentSec already writes (`report.json`, `mcp-report.json`). Overview with a per-scenario grid by attack category, OWASP ASI01-ASI10 coverage, attack-vector…
v0.8.0v0.8.0 · 11 Oct 2026New: delivery tracking and attack goals for scenarios. `Scenario.exposure` names text only the adversarial content contains; a scenario whose content never reached the agent is reported with the new status `inconclusive` (and…
v0.7.00.7.0 · 3 Oct 2026Docs: `docs/testing.md` now lists everything that has not been tested yet (other real agents, Claude Code's built-in tools, sub-agents and memory, real models inside frameworks, ADK and AutoGen multi-agent modes, mem0 with model-based…
v0.6.0v0.6.0 · 24 Sep 2026What's Changed docs: add why-agentsec.md with sourced incidents, adoption data, and … by @tinniaru3005 in https://github.com/invarislabs/invaris-agentsec/pull/17 Rag attack pack by @tinniaru3005 in…
v0.5.1v0.5.1 · 22 Sep 2026Fix: a real bug in the pull-request comparison comment (`pr-comment`) meant it never posted the actual comparison summary -- `action/pr-comment.sh` used `gh api -f body=@file`, and `-f` sends the literal string `"@file"` rather than…
Questions

About Invaris Agentsec

How do I install Invaris Agentsec?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Invaris Agentsec safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Invaris Agentsec still maintained?

Yes — the latest release is v0.9.0 (12 Oct 2026), and the last commit was 6 days ago. The repository has 2 stars.