MCP.so
ログイン

Mcp Knowledge Graph

@shaneholloman

リポジトリ

Mcp Knowledge Graph について

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

#typescript#mcp#knowledge-graph#claude-ai#ai-memory#memory-server

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

shaneholloman

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "Aim-Memory-Bank": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-knowledge-graph",
        "--memory-path",
        "/Users/yourusername/.aim"
      ]
    }
  }
}

ツール

10

Store new memories (people, projects, concepts)

Add facts to existing memories

Link two memories together

Search memories by keyword

Retrieve specific memories by exact name

Read all memories in a database

List available databases

Forget memories

Remove specific facts from a memory

Remove links between memories

概要

What is Mcp Knowledge Graph?

Mcp Knowledge Graph is an MCP server that gives AI models persistent memory through a local knowledge graph. It stores and retrieves information across conversations using entities, relations, and observations, and works with Claude Code/Desktop and any MCP‑compatible AI platform.

How to use Mcp Knowledge Graph?

Add the server to your claude_desktop_config.json or .claude.json using npx -y mcp-knowledge-graph --memory-path <path>. Optionally create a .aim directory in a project for project‑local storage. Once configured, the AI can use tools prefixed with aim_ (e.g., aim_memory_store, aim_memory_search) to manage memories.

Key features of Mcp Knowledge Graph

  • Master Database used by default for all operations
  • Multiple named databases for organizing memories by topic
  • Automatic project‑local memory using .aim directories
  • Location override to force project or global storage
  • Safe operations with built‑in file marker protection
  • Database discovery to list all available stores

Use cases of Mcp Knowledge Graph

  • Remembering user preferences, project details, or personal information across AI conversations
  • Organizing memories into separate databases (work, personal, health) by context
  • Keeping memory files in a synced folder (e.g., Dropbox) for access across multiple machines
  • Project‑local memory that stays within a codebase, with automatic detection via .aim directory

FAQ from Mcp Knowledge Graph

What are the .aim directory and _aim file marker?

The .aim directory is a project‑local folder that triggers automatic memory storage. The _aim marker is a safety line ({"type":"_aim","source":"mcp-knowledge-graph"}) placed at the start of every memory file to prevent accidental overwrites of unrelated JSONL files.

How does storage location work?

If a .aim directory exists in the current project, memory files are stored there. Otherwise, the configured global --memory-path directory is used. You can also force project or global location with an optional location parameter.

How do I use multiple named databases?

Pass a context parameter (e.g., "work", "personal") to memory tools. The system automatically creates new database files (e.g., memory-work.jsonl) alongside the master memory.jsonl. No manual setup is required.

What happens if a file lacks the _aim marker?

The server refuses to write to the file and returns an error: “File does not contain required _aim safety marker”. Either add the marker manually or delete the file and let the system recreate it.

What are the requirements to run this server?

Node.js version 22 or later and an MCP‑compatible AI platform (e.g., Claude Desktop).

コメント

「メモリとナレッジ」の他のコンテンツ

Rust Docs MCP Server

Govcraft

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

286

RAG Documentation MCP Server

hannesrudolph

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

267

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467

Obsidian MCP Server

StevenStavrakis

A simple MCP server for Obsidian

717

Obsidian MCP Server

cyanheads

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

618