ITHZ MCP Server

ITHZ MCP

Project memory that agents can inspect

ITHZ MCP is for teams and power users who want agent memory to live with the project: deterministic context packs, durable decisions, gates, risks, scoped claims and explicit checkpoints.

What it brings

• Different from generic RAG: the project owns the memory zone and the agent asks for bounded context packs.
• Different from chat history: decisions, risks, gates and reviewer notes are stored as project records instead of being buried in a conversation.
• The ledger layer lets a project allow, limit or block claims so agents can distinguish what may be said from what still needs review.
• Large-repo mode prunes generated codec/media/build outputs and keeps intake compact.
• Windows and POSIX host installers cover Codex, Claude Code, Cursor, Antigravity and generic JSON-RPC clients; macOS uses Python stdio until a macOS native binary is available.

Roadmap

• Dogfood on ITHZ projects
• Team memory beta
• Context VCS timeline
• Benchmarks against full-scan and generic RAG workflows

Ledger layer

A project record, not hidden chat memory

The MCP layer is designed around a simple boundary: code stays in Git, short startup rules stay in project.md, and long-lived agent work memory is stored in the local project.ithz archive. That archive can keep decisions, gates, risks, next steps and checkpoints close to the project instead of scattering them across chats or vendor-side memory.

Project Ledger v1 adds a more explicit control surface on top of that memory. A team can record durable decisions, scoped claims, blocked claims, reviewer notes and replication packs. In practice, this helps an agent know not only what the project remembers, but also what it is allowed to claim, what is still conditional and what must not be repeated publicly.

This does not turn ITHZ MCP into a production database, cloud sync product or Git replacement. Git remains the transport and history for source code. ITHZ MCP complements it with auditable work memory: bounded context packs, provenance, redaction checks and a clearer handoff trail for AI-assisted development.

Team outcome

Less context drift between tasks

For a team, the practical value is less context drift. A new agent run can start from project status, workflow profiles and a deterministic context pack before it reads broad source trees. Reviewers get a trail of why something was done, which gates applied, and which claims are safe or blocked.

The public package also keeps the safety boundary visible: raw prompts are not the default public memory surface, sensitive content can be redacted or blocked, and large repositories can avoid turning every task into a full-scan exercise.

Next steps for MCP

MCP is about project-owned memory. The useful next step is to test the package and then understand how Native keeps the archive side inspectable.

Download MCP

Install the current MCP27 agent-memory package for Windows or macOS/POSIX.

Review team path

See how Free Local, Team and Business map to shared project memory.