mcp-lucene-server

mcp-lucene-server

mcp-lucene-server

Category
访问服务器

README

MCP Lucene Server

Description

The MCP Lucene Server is a Java-based implementation of the Model Context Protocol (MCP) designed to provide efficient search and retrieval capabilities using Apache Lucene. This server allows you to manage and query documents, leveraging Lucene's powerful indexing and search features. It is built using Spring Boot for easy setup and deployment.

Features

  • MCP Compliance: Implements the core Model Context Protocol.

  • Lucene-Powered: Utilizes Apache Lucene for full-text search and indexing.

  • RESTful API: Provides a RESTful API for interacting with the server.

  • Document Management:

    • Upsert: Add or update documents in the Lucene index.

    • Delete: Delete documents from the Lucene index.

    • List: Retrieve a list of documents from the index.

  • Querying:

    • Supports complex queries using the Lucene query syntax.

    • Filtering: Filter queries based on document metadata.

  • Status: Check the server status.

  • Spring Boot: Built with Spring Boot for easy setup and deployment.

  • Dockerization: Includes instructions for containerizing the application using Docker.

Table of Contents

Getting Started

Prerequisites

  • Java: Java 11 or higher.

  • Maven: Maven 3.6.0 or higher.

  • Docker: Install Docker if you plan to use the Docker image.

Installation

  1. Clone the repository:

    git clone [https://github.com/your-username/mcp-lucene-server.git](https://github.com/your-username/mcp-lucene-server.git)
    cd mcp-lucene-server
    

    (Replace your-username with your GitHub username)

  2. Build the project using Maven:

    mvn clean install
    

Running the Server

Without Docker

  1. Run the Spring Boot application:

    java -jar target/mcp-lucene-server-0.0.1-SNAPSHOT.jar
    

    (The exact name of the .jar file might vary slightly depending on your project version.)

  2. The server will start on port 8080 by default.

With Docker

  1. Ensure you have Docker installed: Follow the instructions on the official Docker website: https://docs.docker.com/get-docker/

  2. Build the Docker image: Navigate to the root directory of your project in your terminal and run:

    docker build -t mcp-lucene-server .
    
  3. Run the Docker container:

    docker run -p 8080:8080 mcp-lucene-server
    

    This will map port 8080 on your host machine to port 8080 inside the container.

Usage

API Endpoints

The server provides the following API endpoints:

  • GET /mcp/v1/status

    • Returns the status of the server.
  • POST /mcp/v1/upsert

    • Upserts (inserts or updates) one or more documents.

    • Request body:

      {
        "documents": [
          {
            "id": "doc1",
            "text": "This is the text of document 1.",
            "metadata": {
              "category": "example",
              "language": "english"
            }
          },
          {
            "id": "doc2",
            "text": "This is document 2's text.",
            "metadata": {
              "category": "sample",
              "language": "spanish"
            }
          }
        ]
      }
      
  • POST /mcp/v1/query

    • Queries the Lucene index.

    • Request body:

      {
        "queries": [
          {
            "query": "document",
            "top_k": 10,
            "filter": {
              "language": "english"
            }
          },
           {
            "query": "text search",
            "filter": {
               "category": "example"
             }
           }
        ]
      }
      
    • query: The Lucene query string.

    • top_k: (Optional) The maximum number of results to return (default: 10).

    • filter: (Optional) A map of metadata fields and values to filter by.

  • POST /mcp/v1/delete

    • Deletes documents from the Lucene index.

    • Request body:

      {
          "ids": ["doc1", "doc2"]
      }
      
  • GET /mcp/v1/list

    • Lists documents from the Lucene index.

    • Request body:

      {
          "ids": ["doc1", "doc2"]
      }
      

Examples

Get server status:

curl http://localhost:8080/mcp/v1/status

Upsert documents:

curl -X POST 

http://localhost:8080/mcp/v1/upsert 

-H 'Content-Type: application/json' 

-d '{
"documents": [
{
"id": "doc1",
"text": "This is the text of document 1.",
"metadata": {
"category": "example",
"language": "english"
}
},
{
"id": "doc2",
"text": "This is document 2''s text.",
"metadata": {
"category": "sample",
"language": "spanish"
}
}
]
}'

Query documents:

curl -X POST 

http://localhost:8080/mcp/v1/query 

-H 'Content-Type: application/json' 

-d '{
"queries": [
{
"query": "document text",
"top_k": 5,
"filter": {
"language": "english"
}
}
]
}'

Delete documents:

curl -X POST 

http://localhost:8080/mcp/v1/delete 

-H 'Content-Type: application/json' 

-d '{
"ids": ["doc1"]
}'

List documents:

curl -X POST 

http://localhost:8080/mcp/v1/list 

-H 'Content-Type: application/json' 

-d '{
"ids": ["doc1", "doc2"]
}'

Configuration

The server can be configured using Spring Boot's application properties. Here are some of the key properties:

  • server.port: The port the server listens on (default: 8080).

  • lucene.index.path: The path to the Lucene index directory. This is where the indexed data is stored. If not set, a default location is used. It is highly recommended to configure this to a persistent storage location.

You can set these properties in an application.properties or application.yml file in your src/main/resources directory, or by using environment variables.

Example application.properties:

server.port=8080 lucene.index.path=/path/to/lucene/index

License

This project is licensed under the Apache 2.0 License.

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