Search

Draft SOC 2 policies from your AI assistant, via MCP

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

[](https://glama.ai/mcp/servers/sentien-labs/verdictswarm-mcp) 📇 🏠 - Multi-AI crypto token scanner. 6 AI agents independently analyze and debate token risk on Solana, Base, and Ethereum. Detects rug pulls, honeypots, holder concentration, and wash trading through adversarial consensus.

Audit a wallet's active ERC-20 token approvals for drain risk — the #1 way DeFi wallets get emptied. Flags unlimited allowances to EOAs, unknown or upgradeable spenders and returns the revoke calldata. CLEAN/REVIEW/AT_RISK verdict in one call. MCP server

Scan untrusted content for prompt injection and check link reputation before an agent acts

Honeypot detection from TCP timing samples. Statistical fingerprinting to distinguish real services from emulators like Cowrie and Dionaea.

An automated red-teaming and reliability-auditing platform for AI agents - tests for prompt injection, tool hijacking and data exfiltration. Ships as an MCP server.

Transactional SQLite task, workflow, event, payload, and evidence storage for MELRA.

ARGUS — Autonomous AI Red Team Platform. 12 offensive agents attack AI systems, MCP servers, and multi-agent workflows in parallel.

Semantic request filtering and scope control for AI apps.

Chained Harm & Injection Measurement for Evaluating Risks in Agents — a red-team research framework that tests hosted models, agentic apps, RAG pipelines, MCP servers, AI coding assistants, macOS desktop apps, and browser extensions against context-pollution, prompt-injection, and chain-composition attacks.

Scan a repo for hidden prompt-injection before your AI agent trusts it — CLI, MCP server & GitHub Action. Run: npx malskanner <repo>. 0 false positives across 5,620 files.

MCP server for JADX-AI Plugin

Enforra policy enforcement integration for Model Context Protocol (MCP) tool handlers.

TypeScript SDK for verifying and auditing MCP tool passports — OpenTrust trust registry client

Local action firewall for AI agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions

FAULTLINE MCP Guard: local integrity monitor for stdio MCP servers. Detects tool poisoning, changed definitions, and rule violations. pip install mcp-integrity

Authorized Android pentest lab, drivable by hand or by AI — Frida bypass chain, live traffic capture with automatic IDOR flagging, full MCP control plane, web dashboard.

Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.

Agent plugin that scores internal safeguards of MCP servers and AI agents and suggests the safest setup for them - built on OWASP Top 10 for Agentic Applications.