I2IDL Glossary of Digital Learning

io.github.blakeplock由 GitHub 账号 blakeplock 发布v1.0.0更新于 Oct 24, 2026

Public read-only MCP access to digital learning concepts, semantic relationships, and citations.

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆

概览

AI 生成的概览

面向 I2IDL 数字学习术语表的只读远程 MCP 服务：可检索概念、读取定义、沿语义关系浏览，并获取保留引用的上下文。

可以做什么
  • 检索已发布的术语表概念，返回标识符与规范链接
  • 获取单个概念的定义、参考文献与元数据
  • 查看上位、下位与相关概念及其规范标识符
  • 获取有范围限制、保留引用的语义上下文包，用于支撑 AI 回答
适用场景
适合需要权威且可引用的数字学习术语定义的场景，或希望以经过策展的语义参考图谱而非普通网页内容为依据来作答时使用。适用于研究、写作和术语梳理等重视持久标识符与来源溯源的工作。
运行要求
需要访问 id.i2idl.org 的远程 streamable HTTP 端点；未声明任何软件包、API 密钥、环境变量或请求头。需具备对该端点的网络访问。
安装前请注意
四个工具均为只读，服务公开，不索取任何凭据。内容为第三方材料且许可混杂：I2IDL 原创内容一般为 CC BY 4.0，第三方内容保留各自来源的权利，转载前应确认署名要求。定义与关系随编辑发布版本更新，可能在不同版本间变化。

安装

在 SourceWeft 中

  1. 打开 控制台中的 I2IDL Glossary of Digital Learning，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.blakeplock%2Fi2idl-glossary/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "i2idl-glossary-of-digital-learning": {
      "type": "http",
      "url": "https://id.i2idl.org/mcp"
    }
  }
}

README

I2IDL Linked Data

Open, interoperable Linked Data publication and research services for the I2IDL Glossary of Digital Learning. The project combines a curated semantic reference graph with browser-based exploration and experimental scholarly discovery.

Versioning: I2IDL uses one public release sequence (v0.0.88, v0.0.89, …). Each release is classified Content, Platform, or Combined. The public release tag, gs:publicationVersion, and Squarespace displayed version are synchronized for each release, while concept revisions change only when concept-level assertions change. The npm package and MCP registry versions remain separate compatibility identifiers. See the release policy and release checklist.

Current publication: v0.0.93 (Platform release; 420 concepts unchanged). Includes bilingual crawlable concept pages, structured metadata, improved research rankings, and automated SEO regression checks.

Public resources

ResourcePurpose
Glossary of Digital LearningHuman-readable curated concepts, definitions, sources and evidence
Developer portalMCP, REST API, SPARQL, Linked Data, and Graph Explorer entry point
Knowledge Graph ExplorerNavigate semantic relationships, compare concepts, analyze graph structure and discover scholarship
Explorer ActivityPublic 30-day aggregate engagement counts
JSON-LD graphCanonical machine-readable publication
SPARQLRead-only knowledge-graph queries
Persistent namespaceResolvable concept, definition, source and scheme identifiers
MCP for AI assistantsPublic, read-only semantic tools (setup guide)

What the project provides

  • Curation and provenance: Persistent identifiers, definitions, evidence records, editorial collections, citations, rights and source attribution.
  • Semantic interoperability: JSON-LD, SKOS, Dublin Core Terms, Schema.org, PROV-O, controlled relationships and selected external mappings.
  • Graph exploration: Search and navigate a one- or two-hop concept network, shortest paths, comparison tools, field and source analytics.
  • Scholarly discovery: Single-concept and two-to-five-concept OpenAlex searches with publication year, open-access, and citation ranking controls. Results remain uncurated discovery candidates, separate from I2IDL's assertions.
  • Research export: CSV and BibTeX downloads of displayed publications with DOI and selected concept identifiers.
  • Public aggregate activity: Daily pageviews, concept selections, successful research searches, and returned publication counts. These are not unique visitors or unique papers.
  • Machine access: Persistent identifiers, JSON-LD and Turtle, read-only REST API v1, bounded SPARQL, and four read-only MCP tools for compatible AI clients.

Quick start

bash
npm cinpm run validatenpm run relationships:coverage

See validation, deployment, and the release checklist before publication. For deployed-service checks, run npm run validate:live.

Documentation

Editorial boundary and licenses

Interactive analytics and OpenAlex search results do not write new statements into the canonical JSON-LD graph. New definitions, evidence, mappings and relationships require separate editorial review and validation.

Repository software is distributed under Apache License 2.0. I2IDL-original glossary material is generally CC BY 4.0 unless otherwise noted; third-party content retains source-specific rights. See data licensing, semantic relationship policy, and external mappings.

来源：README.md，提交 0754254

工具

4

search_concepts

Search published I2IDL glossary concepts; returns identifiers and canonical URLs.

输入参数limitquery必填

get_concept

Retrieve a glossary concept, definition, references and metadata.

输入参数id必填

get_relationships

Retrieve broader, narrower and related concepts with their canonical identifiers.

输入参数id必填

get_context

Retrieve a bounded, citation-preserving semantic context bundle suitable for grounding AI responses.

输入参数id必填depthmaxRelated

版本历史

1
  1. v1.0.0最新Oct 15, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分