A deterministic MCP server that enforces auditable workflows by requiring AI agents to provide structured justifications and obtain human approval for file operations. It provides a secure, tamper-evident pipeline for tracking agent intent and codebase changes through cryptographic signatures and SQLite indexing.
A self-hosted MCP server providing a governed interface for AI agents to interact with local Docker infrastructure, featuring a two-phase confirm protocol for state-changing operations and append-only audit logging.
A local MCP server that delegates tasks to a subagent runtime via OpenAI-compatible interfaces, enabling file operations, command execution, and rollback of local file changes.
Tamper-evident audit logging for AI agents. Append-only, hash-chained, optionally Ed25519-signed log. The MCP server lets an agent keep and verify a record of what it actually did.
A deny-by-default MCP server for Obsidian vaults where operators declare exact capabilities (list, read, create, etc.) scoped by path globs; everything not permitted is impossible by construction as disallowed tools are never registered.