MCP cover image
See in Github
2025-04-11

MCP服务器用于连接您的类型ensense集合并使用您喜欢的MCP客户端(Claude/ Cursor)检索数据

1

Github Watches

1

Github Forks

2

Github Stars

Tacitbase MCP Server

This is a Machine Comprehension Protocol (MCP) server for Tacitbase that provides advanced search capabilities using both Tacitbase's native search and Typesense for enhanced search features.

Project Structure

The project follows a clean, modular architecture:

.
├── models/      # Data structures and types
├── services/    # Business logic and external service interactions
├── handlers/    # Request handlers and routing logic
├── tools/       # Tool registration and configuration
├── main.go      # Application entry point
└── README.md    # Project documentation

Packages

  • models: Contains all data structures and types used across the application
  • services: Implements the business logic and external service interactions
  • handlers: Contains the request handlers that process incoming requests
  • tools: Registers the tools available for searching candidates

Features

  • Basic keyword search with filtering and sorting
  • Vector search for similarity-based matching
  • Semantic search with natural language understanding
  • Fallback to Tacitbase's native search when needed
  • Tool registration for searching candidates

Search Tools

1. Basic Search (search_candidates)

  • Keyword-based search with typo tolerance
  • Supports field-specific search
  • Filtering and sorting capabilities
  • Group by functionality
  • Exact matching option

2. Vector Search (vector_search_candidates)

  • Similarity search using vector embeddings
  • Ideal for finding candidates with similar profiles
  • Supports hybrid search combining vectors with filters

3. Semantic Search (semantic_search_candidates)

  • Natural language understanding
  • Automatic embedding generation
  • Support for multiple embedding models (OpenAI, SBERT, E5)
  • Hybrid search combining semantic understanding with filters

Configuration

Environment Variables

  • TACITBASE_AUTH_TOKEN: Authentication token for Tacitbase API
  • TYPESENSE_API_KEY: API key for Typesense
  • TYPESENSE_HOST: Typesense host (default: localhost)
  • TYPESENSE_PORT: Typesense port (default: 8108)
  • TYPESENSE_PROTOCOL: Protocol for Typesense (default: http)

Installation

  1. Install dependencies:
go mod download
  1. Build the server:
go build -o tb-mcp-server
  1. Run the server:
./tb-mcp-server

Example Usage

Basic Search

{
  "query": "golang developer",
  "search_fields": "skills,latest_experience",
  "filter_fields": "location:San Francisco",
  "sort_by": "latest_experience:desc",
  "page": 1,
  "per_page": 20
}

Vector Search

{
  "vector_query": "[0.1, 0.2, ..., 0.512]",
  "filter_fields": "years_of_experience:>5",
  "page": 1,
  "per_page": 20
}

Semantic Search

{
  "query": "experienced team lead with cloud architecture background",
  "embedding_model": "openai",
  "filter_fields": "years_of_experience:>8",
  "page": 1,
  "per_page": 20
}

Development

To modify or extend the server:

  1. Edit main.go to add new tools or modify existing ones
  2. Run tests (if any)
  3. Build and test the server

相关推荐

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Contraband Interactive
  • Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.

  • rustassistant.com
  • Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • modelcontextprotocol
  • 模型上下文协议服务器

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • n8n-io
  • 具有本机AI功能的公平代码工作流程自动化平台。将视觉构建与自定义代码,自宿主或云相结合,400+集成。

  • open-webui
  • 用户友好的AI接口(支持Ollama,OpenAi API,...)

  • WangRongsheng
  • 🧑‍🚀 llm 资料总结(数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型)|摘要世界上最好的LLM资源。

    Reviews

    5 (1)
    Avatar
    user_AH5DGWGy
    2025-04-16

    I've been using the typesense-mcp-server by sourabh-khot65, and it's been amazing. The server's seamless integration with MCP applications and its efficient search capabilities have greatly improved my project's performance. The clear documentation and ease of setup make it a solid choice for developers looking for a reliable search solution. Highly recommend checking it out via the provided GitHub link!