Skip to main content
Glama

mnehmos.synch.mcp

npm version CI License: MIT

Global Memory Bank for AI Agents

An MCP server that provides persistent context synchronization for AI agents across sessions and projects.

Features

  • Active Context - Get/set current working state per project

  • Filing Cabinet - Index files with summaries and metadata for fast retrieval

  • Memory Search - Search across all indexed content

  • Spatial Map - "PC as Rooms" folder navigation metaphor

  • Bug Tracking - Log and resolve bugs for agent workflows

  • Lock Management - Concurrent agent access coordination

  • Context Events - Agent-to-agent handoff protocol

Related MCP server: vibe-memory

Installation

Prerequisites: Node.js 18.0.0 or higher

npm install -g mnehmos-synch-mcp

From Source

git clone https://github.com/Mnehmos/mnehmos.synch.mcp.git
cd mnehmos.synch.mcp
npm install
npm run build

Configuration

Add to your MCP client config (Claude Desktop, Cline, etc.):

{
  "mcpServers": {
    "mnehmos-synch-mcp": {
      "command": "npx",
      "args": ["mnehmos-synch-mcp"]
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "mnehmos-synch-mcp": {
      "command": "mnehmos-synch-mcp"
    }
  }
}

Tools

Context Management

Tool

Description

get_active_context

Get current summary/focus for a project

set_active_context

Update active context state

list_projects

List all projects in memory bank

Filing Cabinet

Tool

Description

file_to_cabinet

Index a file with summary and metadata

get_from_cabinet

Retrieve indexed file info

search_memory

Search across all indexed content

Spatial Map

Tool

Description

get_spatial_map

Get folder structure as "rooms"

add_room

Add folder to spatial map

link_rooms

Connect two folders

Bug Tracking

Tool

Description

log_bug

Log a bug for later fixing

get_bugs

Get bugs by project/status

resolve_bug

Mark bug as resolved

Concurrent Access

Tool

Description

acquire_lock

Lock a resource for exclusive access

release_lock

Release a held lock

get_lock_status

Check lock state

Agent Coordination

Tool

Description

emit_context_event

Emit handoff/checkpoint/error events

get_context_events

Get recent context events

Server Configuration

Tool

Description

configure_server

First-run setup for server location

get_server_info

Get server configuration

Usage

// Set active context for a project
await client.callTool("set_active_context", {
  project_id: "my-app",
  summary: "Working on authentication module",
  focus: "src/auth/login.ts"
});

// Index a file
await client.callTool("file_to_cabinet", {
  project_id: "my-app",
  file_path: "src/auth/login.ts",
  summary: "Login handler with JWT validation",
  key_exports: ["login", "validateToken"]
});

// Search memory
await client.callTool("search_memory", {
  query: "authentication",
  project_id: "my-app"
});

// Emit handoff event
await client.callTool("emit_context_event", {
  project_id: "my-app",
  agent_id: "agent-1",
  event_type: "handoff",
  summary: "Completed auth module, ready for testing"
});

Data Storage

Data is stored locally in SQLite with Markdown file fallbacks:

Platform

Location

Windows

%USERPROFILE%\.agent-synch\

macOS/Linux

~/.agent-synch/

Storage includes:

  • agent_synch.db - SQLite database

  • projects/{id}/ - Per-project markdown files

  • .locks/ - Lock files for crash recovery

Development

# Install dependencies
npm install

# Development mode with watch
npm run dev

# Run tests
npm test

# Build for production
npm run build

License

MIT

Author

Mnehmos

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides persistent, searchable memory and knowledge capture for AI-assisted development, enabling agents to retain decisions, bugs, and patterns across sessions and projects.
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables AI coding agents to read and write persistent project-scoped and cross-project memory during sessions, using local semantic search to surface relevant decisions, preferences, error patterns, and guidelines across sessions. It also optionally exposes an autonomous task queue that draws on that same stored context.
    -