"DHL" matching MCP servers:

Enables running any GoHighLevel MCP server behind a policy wrapper that lets AI agents call only allowed tools under specified argument constraints, blocks and logs everything else, and filters tools/list so disallowed tools are hidden.

Tamper-evident cryptographic audit trail for LLM outputs. Compliance logging for AI agent decisions.

An MCP server that enforces plain-English rules on AI agent tool calls, deterministically blocking forbidden actions before execution via a Claude Code hook and a check_action tool.

DCL Trust Oracle is a deterministic AI audit layer, natively integrated with MCP, that evaluates LLM and agent outputs against configurable policies before and after action. Every verdict is written to a tamper-evident, hash-chained audit log storing only cryptographic metadata — never raw content — enabling privacy-first forensic review.

An MCP server protected by Cloudflare Access as a self-hosted application, validating Access JWT and conditionally exposing tools based on user identity.