by swnotmetal
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
npm:koma-gate-mcp · local package57/wkpublished 3 mo ago
Security analysis, scanning and identity.
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.
Microsoft Entra SCIM 2.0 Provisioning API: user and group lifecycle, with a local mock.
MCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.
MCP server library + ratel-mcp CLI: expose a Ratel tool catalog as a Model Context Protocol server. Manage upstream MCP servers, OAuth, and Claude Code import from one binary.
Smart contract security scanner — vulnerabilities, risk scores, and calldata decoding
Model Context Protocol tools for better-compute: pools, capacity, GPU reservations and node status for AI agents, gated by better-iam.
OAuth 2.1 for MCP clients that only know how to send a static Authorization header: a loopback gateway that does RFC 9728 discovery, PKCE and silent refresh on their behalf.
Connect Claude to Microsoft Teams — read/send messages, list channels, search chats.
Read-only runtime secret retrieval from HashiCorp Vault via Keymaster for autonomous AI agents.
MCP server for SAP Datasphere — 39 tools (49 with diagnostics), Smart Query, Streamable HTTP, and built-in config-driven PII/sensitive-field masking (fail-closed, audit-logged, GDPR-ready).
Security scanning and threat detection for AI agents
jwt-lab – A fast, secure, beautiful JWT CLI tool and MCP server for developers & AI agents. Encode, decode, verify, inspect, audit, and generate keys for JSON Web Tokens.
Generador automático de backends con Node.js, Express, Prisma y módulos configurables. Servidor MCP compatible con npx para agentes IA. Soporta PostgreSQL, MySQL, MongoDB y SQLite.
Scan, protect, and monitor APIs from AI coding tools. Device-level rate limiting.
Zero-knowledge encrypted storage for humans and AI agents. Client-side AES-256-GCM, EU-hosted.
Agent policy checks and signup-free trial setup for Allowly workspaces
Security scanner for AI agent packages — CLI + MCP server
Headless-drivable security auditor for Linux, macOS and Windows. Runs a 19-check local audit and can be driven by an AI agent (--capabilities / --audit --json / --fix). Total anonymity by default: no account, no key, no telemetry, and the AI Fix lane reso
Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.