MCP Server

Maintained

MIT

io.github.Intina47/context-sync MCP Server

io.github.Intina47/context-sync

Local-first persistent memory for AI coding tools—sync context across Claude, Cursor, VS Code, and more.

What is the io.github.Intina47/context-sync MCP server?

Context Sync is an MCP server that provides persistent project memory for AI coding agents. It stores and retrieves project identity, tech stack, active work, decisions, and codebase structure across sessions, enabling continuity without relying on model memory alone.

Context Sync solves session continuity by maintaining a local-first memory layer for your codebase. Instead of re-explaining your project each session, it stores project context, decisions, and constraints, then makes them retrievable through MCP tools. It works across Claude Desktop, Cursor, VS Code, Continue, Zed, Windsurf, and other AI tools, with optional read-only Notion integration and git-aware context capture.

How to install io.github.Intina47/context-sync

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "context-sync": {
      "command": "npx",
      "args": [
        "-y",
        "@context-sync/server"
      ]
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "context-sync": {
      "command": "npx",
      "args": [
        "-y",
        "@context-sync/server"
      ]
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "context-sync": {
      "command": "npx",
      "args": [
        "-y",
        "@context-sync/server"
      ]
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "context-sync": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@context-sync/server"
      ]
    }
  }
}

Claude Code

claude mcp add context-sync -- npx -y @context-sync/server

Tools & capabilities

Tools this server exposes to the agent.

set_project — Initialize project context with absolute path; installs git hooks for automatic context capture if in a git repository
remember — Store persistent context about project decisions, constraints, and caveats for future sessions
recall — Retrieve previously stored project context and memories
read_file — Read and inspect specific files in the project
search — Search across project files and context
structure — Explore project structure with configurable depth
git — Git-aware tools including status, context, hotspots, coupling, blame, and analysis
notion — Optional read-only Notion integration for searching and reading pages

Use cases

Start each coding session by recalling project context and structure instead of re-explaining your codebase
Store architectural decisions and constraints that persist across multiple AI conversations
Explore project structure and search files through AI agents without manual context switching
Automatically capture git context (commits, branches, hotspots) for better code understanding
Integrate project documentation from Notion as read-only reference material for AI agents

io.github.Intina47/context-sync MCP server FAQ

What is Context Sync?

Context Sync is an MCP server that provides persistent, local-first memory for AI coding tools. It stores project identity, tech stack, decisions, and codebase structure, making them retrievable across sessions and AI tool switches.

Is Context Sync free?

Yes, Context Sync is open-source and free to use. It stores data locally on your machine.

How do I install it in Cursor or Claude?

Install globally via npm: `npm install -g @context-sync/server`. Auto-configuration runs during install. After install, restart your AI tool and verify that context-sync appears in your MCP tool list.

Do I need authentication?

No authentication is required for core features. Notion integration is optional and requires setup via `context-sync-setup` if you want read-only Notion lookup.

Where is my data stored?

Data is stored locally by default at `~/.context-sync/data.db`. You can customize the database path via CLI flag `--db-path` or environment variable `CONTEXT_SYNC_DB_PATH`.

Which AI tools are supported?

Context Sync works with Claude Desktop, Cursor, VS Code + GitHub Copilot, Continue.dev, Zed, Windsurf, Codeium, TabNine, Codex CLI, Claude Code, and Antigravity.

README (reference)

Source of truth, from the repository.

Context Sync

Local-first project memory for AI coding tools over MCP.

Context Sync gives an agent a persistent memory layer for a codebase:

project identity and tech stack
active work, decisions, constraints, and caveats
structured file exploration
git-aware context
optional read-only Notion lookup

Context Sync

What It Does

Context Sync is built for session continuity. Instead of relying on a model to remember earlier conversations, it stores the project context that matters and makes it retrievable through a small MCP tool surface.

The current core tools are:

set_project
remember
recall
read_file
search
structure
git
notion

Install

Install globally:

npm install -g @context-sync/server

Auto-configuration runs during global install. After install, restart your AI tool.

If you install locally instead of globally, auto-config does not run. Use the manual config guide in docs/CONFIG.md.

Verify

Check that context-sync appears in your MCP tool list:

Claude Desktop: open the tools list
Cursor: open the tools list
VS Code / Copilot Chat Agent mode: check tools
Continue.dev: open the Continue panel
Codex CLI: codex mcp list
Claude Code: claude mcp list

If auto-config fails, use docs/TROUBLESHOOTING.md and docs/CONFIG.md.

Optional Notion Setup

Run the setup wizard if you want Notion integration:

context-sync-setup

or:

npx context-sync-setup

Notion support is intentionally read-only at the tool surface:

notion({ action: "search", query: "..." })
notion({ action: "read", pageId: "..." })

First-Time Workflow

Start every new session by setting the project first:

1. set_project({ path: "/absolute/path/to/project" })
2. recall()
3. structure({ depth: 2 })
4. read_file({ path: "src/index.ts" })
5. remember({ type: "decision", content: "Use SQLite for local storage" })

Recommended pattern:

set_project once per project/session start
recall to recover context
structure and search to explore
read_file for focused inspection
remember when something should survive the current session

Git Integration

When you run set_project inside a git repository, Context Sync can install hooks for automatic context capture.

Installed hooks:

post-commit
pre-push
post-merge
post-checkout

Hooks are marked with Context Sync Auto-Hook, and existing hooks are backed up first.

The git tool supports:

status
context
hotspots
coupling
blame
analysis

Data And Config

Default locations:

Database: ~/.context-sync/data.db
Config: ~/.context-sync/config.json
Install status: ~/.context-sync/install-status.json

Custom database options:

CLI: context-sync --db-path /absolute/path/to/db
Env var: CONTEXT_SYNC_DB_PATH

See docs/DATA.md for storage details.

Supported Platforms

Claude Desktop
Cursor
VS Code + GitHub Copilot
Continue.dev
Zed
Windsurf
Codeium
TabNine
Codex CLI
Claude Code
Antigravity

Docs

View repository →