Binelek MCP Server

Binelek MCP Server

Enables interaction with the Binelek Platform's knowledge graph, search, AI, and data pipeline services through the API Gateway.

Category
访问服务器

README

Binelek MCP Server

Model Context Protocol (MCP) server for the Binelek Platform. This server provides MCP tools for interacting with the Binelek knowledge graph, search, AI, and data pipeline services through the API Gateway.

Features

  • Knowledge Graph Tools: Query, create, update, and delete entities and relationships
  • Search Tools: Semantic, keyword, and hybrid search capabilities
  • AI Tools: Chat with AI, make predictions, analyze entities
  • Pipeline Tools: Trigger and monitor data pipelines
  • Admin Tools: Domain configuration, YAML validation, code generation

Installation

npm install
npm run build

Configuration

Create a .env file (copy from .env.example):

BINELEK_GATEWAY_URL=http://localhost:8092
BINELEK_TENANT_ID=core
BINELEK_JWT_TOKEN=your-jwt-token-here
LOG_LEVEL=info

Usage

As a Standalone Server

npm start

With Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "binelek": {
      "command": "node",
      "args": ["/path/to/binelek-mcp-server/build/index.js"],
      "env": {
        "BINELEK_GATEWAY_URL": "http://localhost:8092",
        "BINELEK_TENANT_ID": "core",
        "BINELEK_JWT_TOKEN": "your-jwt-token"
      }
    }
  }
}

With VS Code Extension

The binelek-vscode-extension uses this MCP server. See that project's README for setup instructions.

Available Tools

Ontology Tools

  • binelek_get_entity - Get entity by ID
  • binelek_query_entities - Execute Cypher queries
  • binelek_create_entity - Create new entities
  • binelek_update_entity - Update existing entities
  • binelek_delete_entity - Delete entities
  • binelek_get_relationships - Get entity relationships
  • binelek_create_relationship - Create relationships

Search Tools

  • binelek_semantic_search - Semantic search using embeddings
  • binelek_keyword_search - Keyword search with Elasticsearch
  • binelek_hybrid_search - Combined semantic + keyword search

AI Tools

  • binelek_ai_chat - Chat with Binelek AI assistant
  • binelek_ai_predict - Make predictions with ML models
  • binelek_ai_analyze_entity - AI-powered entity analysis

Pipeline Tools

  • binelek_list_pipelines - List all pipelines
  • binelek_get_pipeline - Get pipeline details
  • binelek_trigger_pipeline - Trigger pipeline execution
  • binelek_get_pipeline_runs - Get pipeline run history

Admin Tools

  • binelek_list_domains - List available domains
  • binelek_get_domain - Get domain configuration
  • binelek_get_ontology_schema - Get ontology YAML schema
  • binelek_validate_yaml - Validate ontology YAML
  • binelek_generate_code - Generate code from YAML

Authentication

The MCP server uses JWT tokens to authenticate with the Binelek API Gateway. You can:

  1. Set in environment: BINELEK_JWT_TOKEN=your-token
  2. Set in .env file: See .env.example
  3. Pass via MCP config: When configuring in Claude Desktop or VS Code

To obtain a JWT token, authenticate through the Binelek platform or use the auth API:

curl -X POST http://localhost:8092/api/auth/login \
  -H "Content-Type: application/json" \
  -d '{"email":"user@example.com","password":"your-password"}'

Architecture

MCP Client (Claude/VS Code)
  ↓ stdio
MCP Server (this project)
  ↓ HTTP/REST
API Gateway (localhost:8092)
  ↓ routes to
Backend Services (Ontology, Search, AI, Pipeline, etc.)

Important: The MCP server communicates ONLY with the API Gateway, never directly with backend services. This ensures proper authentication, tenant isolation, and rate limiting.

Development

# Install dependencies
npm install

# Build
npm run build

# Development mode (auto-reload)
npm run dev

# Type check
npm run type-check

Error Handling

The server handles errors gracefully and returns them in MCP format:

{
  "content": [{
    "type": "text",
    "text": "Error: Entity not found: prop_123"
  }],
  "isError": true
}

License

MIT

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