akasha-os/mcp

Productivity workflow

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

0 stars 0 forks 品質 65 トレンド 4MIT

Repository Install

Akasha MCP server — use your second brain in Claude and other LLMs

概要

Akasha MCP server — use your second brain as context in Claude, Cursor, and any other MCP-compatible LLM tool. Connect Akasha to Claude Desktop and every conversation automatically has your full context — your projects, decisions, recent activity, and knowledge graph. - A running Akasha instance - An Akasha API key (generated in your workspace settings) ~/Library/Application Support/Claude/claude_desktop_config.json %APPDATA%\Claude\claude_desktop_config.json Restart Claude Desktop. You should see Akasha appear in the tools panel. Claude will query your Akasha graph and answer from your actual context — not from thin air. The MCP server only exposes data from your own Akasha instance. Private nodes are never included in MCP responses. You control what is accessible via workspace settings.

README

@akasha/mcp

Akasha MCP server — use your second brain as context in Claude, Cursor, and any other MCP-compatible LLM tool.

Connect Akasha to Claude Desktop and every conversation automatically has your full context — your projects, decisions, recent activity, and knowledge graph.

Requirements

A running Akasha instance
An Akasha API key (generated in your workspace settings)

Claude Desktop setup

Add this to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "akasha": {
      "command": "npx",
      "args": ["@akasha-os/mcp"],
      "env": {
        "AKASHA_URL": "http://localhost:3000",
        "AKASHA_API_KEY": "your-api-key"
      }
    }
  }
}

Restart Claude Desktop. You should see Akasha appear in the tools panel.

Available tools

Tool	Description
`search_graph`	Search your knowledge graph by keyword or concept
`get_project_context`	Full context for a project — activity, documents, decisions
`get_today_context`	Today’s biometrics, tasks, open loops, and agent insights
`get_recent_activity`	Your activity from the last N hours across all sources
`get_insights`	Unread agent insights and nudges

Example

Once connected, ask Claude:

What should I focus on today?
Catch me up on the Akasha project
What do I know about vector databases?
Who have I talked to most about this topic?

Claude will query your Akasha graph and answer from your actual context — not from thin air.

Privacy

The MCP server only exposes data from your own Akasha instance. Private nodes are never included in MCP responses. You control what is accessible via workspace settings.

Links

GitHub で README 全文を見る

インストール

npx @akasha-os/mcp

MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "akasha": {
      "command": "npx",
      "args": ["@akasha-os/mcp"],
      "env": {
        "AKASHA_URL": "http://localhost:3000",
        "AKASHA_API_KEY": "your-api-key"
      }
    }
  }
}