EleSync is a local-first memory vault for AI tools that stores notes, preferences, project facts, and conversations in a user-controlled folder. It provides a local dashboard, CLI, import/export, search, encryption, and MCP access so AI clients can read and write memories from the same vault.
From the registry: Local-first MCP memory vault: files you own, shared across ChatGPT, Claude, Gemini & any MCP client
$ pipx install elesynchttps://pypi.org/project/elesync/$ ele onboardPlease install the `elesync` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install EleSync** — Install the EleSync CLI/server. The most portable path in the README is via pipx. Run: `pipx install elesync` (https://pypi.org/project/elesync/)
- **Python 3.10+** — Python 3.10 or newer is required for the pipx/pip install path. (https://www.python.org/downloads/)
- **Initial onboarding** — Run EleSync onboarding once to choose a vault location and complete first-run setup before connecting an AI client. Run: `ele onboard`
Canonical MCP server config (stdio transport):
- command: `ele`
- args: ["serve"]
Note: EleSync supports both stdio and HTTP transports, but for local desktop/editor clients the README says it usually runs through stdio via `ele serve`, which is the simplest canonical config. For clients needing a network endpoint, use EleSync's HTTP serving flow (`ele connect ...` / `ele serve --transport http ...`), but the README does not provide a single canonical HTTP URL/headers shape to extract here. No environment variables are documented for the stdio configuration.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.An MCP Server for computer-use in Windows OS