Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
bla
MCP servers🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.
git clone https://github.com/qybaihe/bla.git -
agent-opfor
MCP serversOpen-source adversary emulation for AI agents and MCP servers.
git clone https://github.com/KeyValueSoftwareSystems/agent-opfor.git -
Execute adversarial-suffix-mcp
MCP serversPremium agentic endpoint for adversarial-suffix-mcp.
-
Execute adversarial-prompt-shield-mcp
MCP serversPremium agentic endpoint for adversarial-prompt-shield-mcp.
-
Viper
MCP serversAdversary simulation and Red teaming platform with AI
git clone https://github.com/FunnyWolf/Viper.git -
invaris-agentsec
MCP serversAdversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.
git clone https://github.com/invarislabs/invaris-agentsec.git -
nuguard
MCP serversAI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
git clone https://github.com/NuGuardAI/nuguard.git -
DialectOS
MCP serversSpanish dialect localization MCP server: 25 regional variants, glossary, adversarial QA gates.
-
AgentTrust
MCP serversQuality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
mcp-agenttrust@0.1.1 -
Eclipse Redteam MCP
MCP serversAdversarial simulation for AI agents — sandboxed twins only.
-
Fable Mode
MCP serversMechanical write gates, evidence receipts, and adversarial review for AI coding agents.
fable-engine@1.3.5 -
AgentTrust
MCP serversQuality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
mcp-agenttrust@0.1.2 -
agent-conductor
MCP serversAGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.
@cubiczan/agent-conductor@0.1.0 -
TAR Engine
MCP serversAudit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.
tar-engine@0.4.0 -
GAUNTLEX
MCP serversConcurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.
gauntlex-ai@1.0.2 -
Edgehound
MCP serversWrites adversarial test suites for AI-built code. Your agent's test engineer.
-
mitre-attack-mcp
MCP serversSearch the MITRE ATT&CK enterprise knowledge base for adversary techniques and tactics.
@mrfentmen/mitre-attack-mcp@1.0.0 -
mitre-atlas-mcp
MCP serversMITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...
mitre-atlas-mcp@1.0.9 -
irrational
MCP serversAdversarial behavioural-bias engine: audits your decisions for cognitive biases via your own AI.
irrational@0.1.0 -
Second Opinion
MCP serversAdversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.
-
vibe-gate-mcp
MCP serversAdversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock
vibe-gate-mcp@0.1.12 -
SentEdge Idea Machine
MCP serversBuy adversarially-debated AI product ideas over x402: $0.10 pulls, $1 buyouts, USDC on Base.
-
alex-llm-attack-mcp-server
MCP serversQuery and retrieve information about various adversarial tactics and techniques used in cyber atta…
-
EthersFlow — Trust Gate for AI Agents
MCP serversTrust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
@ethersflow/mcp-server@0.3.1
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.