Graphiti MCP Server

Graphiti MCP Server

Enables users to query a comprehensive knowledge graph of personality psychology containing over 16,000 nodes covering traits, frameworks, and assessments. It supports semantic search of facts and entities, relationship extraction, and the ability to add new information to the graph.

Category
访问服务器

README

Graphiti MCP Server (Personality Knowledge Graph)

A private MCP server for querying a personality psychology knowledge graph, powered by Graphiti and Neo4j Aura.

Features

  • Knowledge Graph: 16,000+ nodes covering personality psychology research, traits, types, frameworks, and assessments
  • Semantic Search: Search facts and entities using natural language
  • MCP Protocol: Compatible with Claude, Cursor, and other MCP clients
  • Cloud Hosted: Runs on Railway with Neo4j Aura backend

Quick Start

For MCP Clients (Cursor, Claude Desktop)

Connect to the hosted server:

{
  "mcpServers": {
    "personality-knowledge": {
      "url": "https://YOUR_RAILWAY_URL/mcp/"
    }
  }
}

Local Development

  1. Clone and install dependencies:
git clone https://github.com/YOUR_USERNAME/graphiti-mcp-server.git
cd graphiti-mcp-server
uv sync
  1. Set environment variables:
cp .env.example .env
# Edit .env with your credentials
  1. Run the server:
uv run main.py --config config/config-aura.yaml

Configuration

The server is configured via YAML files in config/:

  • config-aura.yaml - Production config for Neo4j Aura
  • config-docker-neo4j.yaml - Local development with Docker Neo4j

Required Environment Variables

Variable Description
NEO4J_URI Neo4j Aura connection URI
NEO4J_USER Neo4j username (usually neo4j)
NEO4J_PASSWORD Neo4j password
OPENAI_API_KEY OpenAI API key for LLM/embeddings

Available MCP Tools

  • search_nodes - Search for entity summaries by semantic similarity
  • search_facts - Search for relationships/facts between entities
  • get_entity_edge - Get details of a specific relationship
  • get_episodes - Get recent episodes for a group
  • add_episode - Add new information to the knowledge graph
  • get_status - Check server and database status

Deployment

Railway

  1. Create a new Railway project
  2. Connect this repository
  3. Set environment variables in Railway dashboard
  4. Deploy

The railway.toml and docker/Dockerfile.standalone are pre-configured for Railway deployment.

Knowledge Graph Contents

This instance contains indexed personality psychology textbooks covering:

  • Personality Traits: Big Five, HEXACO, temperament dimensions
  • Personality Types: MBTI, Enneagram, Socionics
  • Frameworks: Theoretical models and assessment frameworks
  • Researchers: Key figures in personality psychology
  • Assessments: Psychological inventories (NEO-PI-R, HEXACO-PI-R, etc.)

License

This MCP server configuration is for private use. The underlying Graphiti framework is licensed under Apache 2.0.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选