Zephr Docs

Getting started

Zephr is an MCP evidence memory. In local mode it runs entirely on your machine over stdio JSON-RPC, storing evidence in a single SQLite file scoped by worktree. Nothing leaves your machine in local mode: the server speaks stdio to the client that launched it, and the database is a file you own.

This section walks you through the flow end to end:

  1. Prerequisites and install — clone, install, build.
  2. Connect your client — point your MCP client at the server.
  3. Your first recall — capture and retrieve a belief.
  4. Claude Code memory plugin — plugin install, rollback, kill switch, and troubleshooting.

Prerequisites

Before you begin, confirm:

  • Node.js 24.x — CI enforces Node 24; engines.node is >=24 <25.
  • pnpm — the workspace installs with pnpm install --frozen-lockfile.
  • An MCP client — Claude Code, Cursor, or any stdio JSON-RPC MCP consumer.

The only prerequisite that is easy to get wrong is Node — the workspace pins Node 24, and a mismatched runtime fails at build rather than at first tool call.

Important: admission is required

zephr-mcp is admission-scoped. Do not connect a bare zephr-mcp process with only ZEPHR_DB_PATH for real work. Use the trusted launcher, which mints a single-use capability and binding before any tool call is allowed. See Connect.