A reference MCP server demonstrating safe agent access to multi-tenant CRM data with tenant isolation enforced in the data layer, role-based permissions, and human confirmation on writes.
A compact MCP server demonstrating explicit tool boundaries, least-privilege discovery, execution-time authorization, destructive-action confirmation, and metadata-only audit logs using a local note store.
Security-enforcing MCP proxy that sits between an AI agent and any number of downstream MCP servers, intercepting every tool call through a capability-token policy gateway that can allow, deny, or escalate to human approval before the call reaches any real tool. It also exposes built-in operator tools for approval workflows, audit trail queries, token management, voice/HUD output, and hierarchical
A secure MCP server enabling tool calls (kb_search, read_doc, publish_report) through a zero-trust CapabilityBroker with OWASP LLM Top-10 guardrails and human-in-the-loop approval.
A secure MCP server for CRM operations (contacts and deals) with Auth0 OIDC authentication, role-based access control (sales-rep read-only vs sales-manager full access), and on-behalf-of token exchange.
MCP server that gives AI agents controlled access to a building services company's daily operations, including customer records, scheduling, and offer calculations. All write operations are protected by a two-stage approval mechanism with time-limited tokens to prevent unauthorized changes.