Yet Sparql MCP Server

@yet-market

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

yet-market

提交者

Sidali Temkit

关于 Yet Sparql MCP Server

MCP SPARQL Server is a high-performance, configurable server that connects to any SPARQL endpoint and provides enhanced functionality including result formatting and caching. It's built on top of the MCP (Message Carrying Protocol) framework to provide a seamless, language-agnost

#yet#mcp #sparql

Yet Sparql MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": [
    {
      "name": "sparql",
      "command": "python3",
      "args": [
        "/path/to/server.py",
        "--endpoint",
        "https://data.legilux.public.lu/sparqlendpoint",
        "--format",
        "simplified",
        "--cache-enabled",
        "true",
        "--cache-ttl",
        "300",
        "--cache-strategy",
        "lru"
      ],
      "env": {
        "SPARQL_ENDPOINT": "https://data.legilux.public.lu/sparqlendpoint",
        "SPARQL_TIMEOUT": "30",
        "SPARQL_MAX_RESULTS": "1000",
        "SPARQL_CACHE_ENABLED": "true",
        "SPARQL_CACHE_TTL": "300",
        "SPARQL_CACHE_MAX_SIZE": "100",
        "SPARQL_CACHE_STRATEGY": "lru",
        "PYTHONPATH": "/path/to/project/directory"
      },
      "transport": "stdio"
    }
  ],
  "defaultServer": "sparql"
}

Yet Sparql MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Yet Sparql Mcp Server?

Yet Sparql Mcp Server is a configurable server that connects to any SPARQL endpoint and provides result formatting and caching. It is built on the Message Carrying Protocol (MCP) framework to offer a language-agnostic interface for querying semantic data.

How to use Yet Sparql Mcp Server?

Install via pip install mcp-server-sparql or from source. Start the server by specifying a SPARQL endpoint: mcp-server-sparql --endpoint URL. Queries are sent using the MCP client with JSON actions that include a query_string and optional format parameter. The server can run in foreground mode, as a background daemon, or as a systemd service.

Key features of Yet Sparql Mcp Server

Connects to any SPARQL-compliant endpoint
Supports SELECT, ASK, CONSTRUCT, and DESCRIBE queries
Outputs JSON, simplified JSON, or tabular formats
Configurable caching with LRU, LFU, and FIFO strategies
Deployable as foreground process, daemon, or systemd service

Use cases of Yet Sparql Mcp Server

Querying public or private SPARQL endpoints from MCP‑compatible applications
Presenting SPARQL results in a table format for UI components
Caching frequently run queries to reduce endpoint load
Integrating semantic data workflows into automated pipelines

常见问题

What are the system requirements?

Python 3.8 or newer is required, along with the `SPARQLWrapper`, `mcp`, `pydantic`, and `python-daemon` libraries.

Can I use any SPARQL endpoint?

Yes, the server is designed to work with any SPARQL-compliant endpoint by specifying its URL via `--endpoint` or the `SPARQL_ENDPOINT` environment variable.

What result formats does the server support?

Three formats are available: standard JSON (default), simplified JSON (key-value pairs), and tabular (columns and rows). You can set the format at startup with `--format` or per query with the `format` parameter.

How does the caching system work?

The server supports three cache replacement strategies: LRU (least recently used, default), LFU (least frequently used), and FIFO (first in first out). You can configure cache TTL, maximum size, and enable/disable caching via command‑line arguments or environment variables.

Can I run the server as a background service?

Yes, use `--daemon` to run as a background process, and optionally set up a systemd service using the provided installation script. Logs and PID files are configurable.

其他分类下的更多 MCP 服务器

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

EverArt