Skip to main content
Glama
Manalink MCP Server

Manalink MCP Server

by TeXmeijin

Manalink MCP Server

Manalink's Model Context Protocol (MCP) server implementation, allowing AI assistants to use features such as teacher search.

function

This MCP server provides the following tools:

  1. Obtain subject master : Obtain master of subject name and subject ID

  2. Get feature master : Get the master of course features (dynamically obtained from API)

  3. Get grade master : Get master of grade name and ID

  4. Teacher search (detailed) : Search for teachers by detailed parameters such as subject ID, grade ID, etc.

Related MCP server: OpenEdu MCP Server

Prerequisites

  • Node.js 18+

  • npm or yarn

install

# リポジトリのクローン
git clone [リポジトリURL]
cd manalink-mcp

# 依存関係のインストール
npm install

How to use

Development Mode

npm run dev

Production Mode

npm run build
npm start

Integration with Claude for Desktop

To use it with Claude for Desktop, add the setting to the claude_desktop_config.json file.

  1. Open the Claude for Desktop configuration file

code ~/Library/Application\ Support/Claude/claude_desktop_config.json
  1. Add the following settings

{
    "mcpServers": {
        "manalink": {
            "command": "node",
            "args": [
                "/絶対パス/manalink-mcp/dist/index.js"
            ]
        }
    }
}
  1. Restart Claude for Desktop

MCP Tools

1. Obtaining subject master

// ツール名: get_subject_master
// パラメータ: なし

2. Obtaining feature master data

// ツール名: get_course_features
// パラメータ: なし

3. Obtain grade master data

// ツール名: get_grade_master
// パラメータ: なし

4. Teacher search (detailed)

// ツール名: search_teachers_advanced
// パラメータ:
// - subject_ids: 科目IDの配列(オプション)
// - grade_ids: 学年IDの配列(オプション)
// - course_feature_id: 特徴ID(オプション)
// - sort: ソート順(オプション)[pr, certification, rating, lesson_count, latest]
// - desired_teaching_period: 指導期間(オプション)[monthly, once]

How to Test

You can use MCP Inspector to verify.

  1. Run the build and then run the inspector

npm run build
npx @modelcontextprotocol/inspector node dist/index.js

license

MIT

HTML to Markdown conversion feature

It implements a function to convert HTML content obtained from Manalink into Markdown format.

How to install

npm install node-html-markdown

How to use

import { convertHtmlToMarkdown } from './utils/api';

// HTMLからMarkdownへの変換
const html = `
  <div>
    <h1>マナリンク</h1>
    <p>オンライン家庭教師プラットフォーム</p>
    <ul>
      <li><a href="/about">サービスについて</a></li>
      <li><a href="/teachers">先生を探す</a></li>
    </ul>
  </div>
`;

const markdown = convertHtmlToMarkdown(html);
console.log(markdown);

Conversion results

The above HTML will generate the following markdown:

# マナリンク

オンライン家庭教師プラットフォーム

* [サービスについて](/about)
* [先生を探す](/teachers)

Markdown conversion of teacher search results

The Teacher Search API allows you to retrieve search results in both HTML and Markdown formats:

import { searchTeachers } from './utils/api';

// 数学の中学生を教えられる先生を検索
const result = await searchTeachers({
  subject_ids: [2], // 数学
  grade_ids: [4], // 中学1年生
  sort: 'rating'
});

// HTML形式の検索結果
console.log(result.bodyContent);

// Markdown形式の検索結果
console.log(result.markdown);

Available Tools

4 tools
get_course_featuresB

コース特徴マスタを取得します。このマスタの取得を通じて、特徴のラベルとIDの対応を取得します。

Inputs: no named parameters.

get_grade_masterB

学年マスタを取得します。このマスタの取得を通じて、学年のラベルとIDの対応を取得します。

Inputs: no named parameters.

get_subject_masterB

科目マスタを取得します。このマスタの取得を通じて、科目のラベルとIDの対応を取得します。

Inputs: no named parameters.

search_teachers_advancedC

科目、学年、特徴、ソート順、指導期間を指定して先生を検索します

Inputs: course_feature_id, desired_teaching_period, grade_ids, sort, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: three tools retrieve specific master data (course features, grade, subject), while the fourth performs an advanced search combining those elements. There is no overlap in functionality, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with 'get_' for retrieval operations and 'search_' for the search function. The naming is uniform and predictable across all four tools, enhancing readability and usability.

    Tool Count4/5

    With 4 tools, the count is reasonable for a server focused on educational data management. It covers core master data retrieval and a search function, though it might feel slightly thin if more operations (e.g., updates or deletions) are expected in the domain.

    Completeness3/5

    The tools provide good coverage for retrieving master data and searching teachers, but there are notable gaps: no CRUD operations for creating, updating, or deleting records, which limits full lifecycle management. The search tool is comprehensive, but the set lacks broader operational capabilities.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      A Model Context Protocol server that enhances AI agents by providing deep semantic understanding of codebases, enabling more intelligent interactions through advanced code search and contextual awareness.
      91
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive Model Context Protocol server providing educational resources and curriculum planning support with intelligent filtering across multiple educational APIs.
      13
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides AI assistants with direct access to local document collections through full-text search, supporting multiple formats and hierarchical collections.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Model Context Protocol servers for Microsoft 365, enabling AI assistants to interact with Calendar, Contacts, OneDrive, Outlook, and SharePoint via the Microsoft Graph API.
      MIT