Security

Universal AI API Orchestrator — 1,554 tools, 96 services. One install.

AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows.

Production-ready MCP server framework with concurrency control, auth, and observability

Memory + wallet for AI agents. Real payment rails, Agent FICO 300-850, Merkle audit, identity.

Zero-dependency trustless governance for the SERVICE side. An MCP server or API re-verifies a calling agent's signed request against the agent's own published policy — so an agent that ignores its own guard still cannot make your service act.

Local-only configuration disclosure CLI for AI agent/MCP setups — reports what it found, what it did not find, and what it cannot see

Local email connectivity for AI agents — read, draft, send, and organize Outlook mail via MCP

MCP server for FlowNest. Drive FlowNest (tasks, comments, cycles, branches) from Claude Code, Claude Desktop, claude.ai web, or any MCP client via a Personal Access Token - locally over stdio, or hosted over Streamable HTTP with OAuth 2.1.

AgentX MCP client — typed access to the AgentX Gateway MCP server (40 tools): IdentityRegistry reads, subscription plans/actions, centralized agents (C-6, off-chain), A2A, reputation, config, endpoints, dialogue & parallel task management.

OAuth 2.1 and enterprise SSO for remote MCP servers—without API keys in client configs.

Token providers for MCP ABAP ADT auth-broker

MCP remote proxy with OAuth — Abluva fork with mid-session re-auth, reliable OAuth callback handling, and MCP 2026-07-28 stateless support

Security scanner for MCP server configurations. Finds risky tools, vulnerable packages, and suspicious servers across Claude Desktop, Cursor, VS Code, and more.

JWT authentication broker for MCP ABAP ADT - manages tokens based on destination headers

Dynamic MCP server toolkit for runtime toolset management with Fastify transport and meta-tools

The wallet an AI agent carries — mandate, budget, vault, and audit. Counterparties verify first.

Grade an MCP server's auth against the spec and diagnose which layer a failure is in.

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.