Skip to main content
Glama
enesjakozh
sdi2200262

eClass MCP Server

by sdi2200262
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

eClass MCP サーバー

特徴

  • 認証: UoAのCAS SSO認証システムを通じてeClassにログインします。

  • コース管理: 登録したコースのリストを取得する

  • セッション管理: ツール呼び出し間の認証されたセッションを維持する

  • ステータスチェック: 認証ステータスを確認する

Related MCP server: mcpUPB

プロジェクト構造

このプロジェクトは、保守性を向上させるためにモジュール式アーキテクチャを採用しています。

eclass-mcp-server/
├── run_server.py               # Entry point script for running the server
├── pyproject.toml              # Project configuration and dependencies
├── .env                        # Environment variables (create from example.env)
├── src/
    └── eclass_mcp_server/      # Main package
        ├── __init__.py         # Package initialization
        ├── server.py           # Core server implementation and tool handlers
        ├── authentication.py   # Authentication functionality 
        ├── course_management.py # Course-related functionality
        ├── html_parsing.py     # HTML parsing utilities
        └── test/               # Test scripts for functionality verification
            ├── __init__.py
            ├── test_login.py
            ├── test_courses.py
            └── run_all_tests.py

インストール

UV を使用してサーバーをインストールします (推奨):

# Clone the repository
git clone https://github.com/yourusername/eClass-MCP-server.git
cd eClass-MCP-server

# Install dependencies
uv sync --dev --all-extras

あるいは、pip を使用してインストールします。

pip install -e .

構成

次の構成でルート ディレクトリに.envファイルを作成します (または、提供されているexample.envファイルをコピーして名前を変更します)。

ECLASS_URL=https://eclass.uoa.gr
ECLASS_USERNAME=your_username
ECLASS_PASSWORD=your_password

すべての資格情報は.envファイルで提供する必要があります。サーバーは資格情報をパラメータとして受け入れません。

使用法

ターミナル

エントリ ポイント スクリプトを使用してサーバーを実行します。

python run_server.py

またはモジュールとして:

python -m src.eclass_mcp_server.server

カーソル

「設定」→「MCP」に移動し、 Add new MCP serverをクリックします。

  • エージェントがサーバーの用途を認識できるように、一意かつ適切な名前を選択します（例：「eClass Server」）

  • 「タイプ」のcommandオプションを選択します

  • コマンド入力に以下を追加します: python /path/to/eclass-mcp-server/run_server.py

このコマンドは、MCP クライアントをserver.pyのメイン サーバー エントリ ポイントに接続するrun_server.pyスクリプトを実行します。

クロードデスクトップ

Claude Desktop で使用するには:

  1. クロードデスクトップを開く

  2. 設定 > サーバーに移動

  3. 次の詳細で新しいサーバーを追加します。

    • 名前: eClass MCP

    • コマンド: run_server.py スクリプトへのパス

  4. サーバーの追加をクリック

  5. クロードとチャットするときにドロップダウンからサーバーを選択してください

ツール

サーバーは、MCP クライアントで使用するための次のツールを提供します。

ログイン

SSO 認証を使用して eClass にログインします。

{
  "random_string": "any_value"
}

コースを取得する

登録済みのコースのリストを取得します (最初にログインする必要があります)。

{
  "random_string": "any_value"
}

ログアウト

eClass からログアウトします。

{
  "random_string": "any_value"
}

認証ステータス

現在の認証ステータスを確認します。

{
  "random_string": "any_value"
}

テスト

このプロジェクトには、機能性を検証するためのテスト スクリプトが含まれています。

# Run all tests
python -m src.eclass_mcp_server.test.run_all_tests

# Run specific tests
python -m src.eclass_mcp_server.test.test_login
python -m src.eclass_mcp_server.test.test_courses

MCPクライアントの使用例

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
import asyncio

async def run_agent():
    server_params = StdioServerParameters(
        command="python /path/to/eclass-mcp-server/run_server.py",
    )
    
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            # Initialize the session
            await session.initialize()
            
            # Login to eClass
            login_result = await session.call_tool("login", {
                "random_string": "dummy"
            })
            print(login_result)
            
            # Get courses
            courses_result = await session.call_tool("get_courses", {
                "random_string": "dummy"
            })
            print(courses_result)
            
            # Logout
            logout_result = await session.call_tool("logout", {
                "random_string": "dummy"
            })
            print(logout_result)

if __name__ == "__main__":
    asyncio.run(run_agent())

AIエージェントとの統合

このMCPサーバーは、モデルコンテキストプロトコルをサポートするAIエージェントと連携して使用するように設計されています。これにより、AIシステムはeClassと直接やり取りできるようになり、以下のような機能を実現できます。

  • コース情報の取得

  • コースのお知らせを確認する

  • コース教材へのアクセス

  • 課題の提出（将来の機能）

セキュリティに関する考慮事項

  • サーバーは機密性の高い認証資格情報を処理します

  • 認証情報は認証にのみ使用され、永続的に保存されることはありません

  • セッションクッキーはサーバーのライフサイクル中にメモリ内に保持されます

  • サーバーは操作を実行する前にセッション状態を検証します

  • 資格情報を含む.envファイルはバージョン管理にコミットしないでください (.gitignore に含まれています)

ライセンス

MITライセンス

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。

Available Tools

4 tools
authstatusB

Check authentication status with eClass

ParametersJSON Schema
NameRequiredDescriptionDefault
random_stringYesDummy parameter for no-parameter tools

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states the purpose without disclosing behavioral traits such as whether it requires authentication, what the response format is, or any rate limits. For a tool with zero annotation coverage, this is inadequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It's appropriately sized and front-loaded, making it easy to understand immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., success/failure, user details) or any behavioral context, which is necessary for an authentication-related tool with no structured data support.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the schema fully documents the single parameter. The description doesn't add any parameter information, which is acceptable since the schema handles it. With 0 parameters of real semantic weight (the parameter is a dummy), a baseline of 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'Check authentication status with eClass', which is a specific verb ('Check') and resource ('authentication status') combination. It doesn't explicitly distinguish from siblings like 'login' or 'logout', but the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'login' or 'logout'. The description states what it does but offers no context about when it should be invoked or what scenarios it addresses.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_coursesB

Get list of enrolled courses from eClass

ParametersJSON Schema
NameRequiredDescriptionDefault
random_stringYesDummy parameter for no-parameter tools

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions retrieving a list but doesn't specify whether this requires authentication, what format the list is in, if there are rate limits, or any error conditions. For a read operation with zero annotation coverage, this leaves significant gaps in understanding the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no wasted words. It's front-loaded with the core purpose ('Get list of enrolled courses from eClass'), making it easy to understand immediately. Every word earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and a simple read operation, the description is incomplete. It lacks details on authentication requirements, return format, error handling, or any behavioral context. For a tool that likely interacts with an eClass system, this leaves too many unknowns for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter (random_string) with 100% description coverage, indicating it's a dummy parameter for no-parameter tools. The description doesn't add any parameter details beyond the schema, but since this is effectively a zero-parameter tool (with a dummy parameter), the baseline is 4 as it doesn't need to compensate for schema gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get list') and target resource ('enrolled courses from eClass'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools (authstatus, login, logout) which are unrelated authentication tools, so this distinction isn't needed but the purpose remains clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. While the sibling tools are unrelated (authentication vs. data retrieval), there's no explicit mention of prerequisites like needing to be logged in or any context for usage. It simply states what it does without usage instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

loginB

Log in to eClass using username/password from your .env file through UoA's SSO. Configure ECLASS_USERNAME and ECLASS_PASSWORD in your .env file.

ParametersJSON Schema
NameRequiredDescriptionDefault
random_stringYesDummy parameter for no-parameter tools

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions authentication via SSO and .env file usage, but lacks details on what the tool actually does (e.g., establishes a session, returns tokens, handles errors) or behavioral traits like rate limits, side effects, or response format. For a login tool with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences that efficiently convey the core functionality and configuration requirement. It's front-loaded with the main action and wastes no words, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a login operation (authentication, session management) with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after login (e.g., session persistence, return values, error handling), leaving gaps in understanding the tool's behavior and outcomes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 1 parameter with 100% coverage, describing it as a 'Dummy parameter for no-parameter tools.' The description doesn't add any parameter-specific information, which is appropriate since the tool likely doesn't require user-provided inputs. With high schema coverage and no meaningful parameters, a baseline of 4 is justified as the description doesn't need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Log in to eClass using username/password from your .env file through UoA's SSO.' It specifies the action (log in), target system (eClass), and authentication method (SSO with .env credentials). However, it doesn't explicitly differentiate from sibling tools like 'authstatus' or 'logout' beyond the obvious login/logout distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: it should be used to authenticate with eClass via SSO when credentials are stored in .env. However, it doesn't provide explicit guidance on when to use this vs. alternatives like 'authstatus' (which might check login state) or prerequisites beyond .env configuration. The guidance is somewhat implied but not comprehensive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

logoutB

Log out from eClass

ParametersJSON Schema
NameRequiredDescriptionDefault
random_stringYesDummy parameter for no-parameter tools

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Log out' implies session termination, it doesn't specify what gets invalidated, whether this affects other tools, if re-authentication is required afterward, or what happens on failure. The description lacks important behavioral context for a security-sensitive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is maximally concise with just three words that directly convey the tool's purpose. There's zero waste or unnecessary elaboration, and it's perfectly front-loaded with the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a security operation like logout with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after logout, whether the operation can fail, what state changes occur, or how this affects subsequent tool calls. The minimal description leaves critical behavioral questions unanswered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the single parameter clearly documented as a 'Dummy parameter for no-parameter tools.' The description doesn't need to add parameter semantics since the tool conceptually requires no real parameters, and the schema adequately explains the dummy parameter requirement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Log out') and target system ('from eClass'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'login' or 'authstatus' beyond the obvious action difference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'authstatus' to check login state, or whether logout should follow certain workflows. It simply states what the tool does without context about appropriate usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 4 tool updates
    • First observedauthstatus
    • First observedget_courses
    • First observedlogin
    • First observedlogout
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a distinct purpose with no overlap: authstatus checks authentication state, get_courses retrieves course data, login handles authentication, and logout terminates sessions. The descriptions clearly differentiate these functions, making tool selection straightforward for an agent.

Naming Consistency4/5

Three tools follow a consistent verb_noun pattern (get_courses, login, logout), while authstatus uses a compound noun. This minor deviation slightly reduces consistency, but the naming remains readable and intuitive overall.

Tool Count4/5

Four tools are reasonable for an eClass server focused on authentication and basic course access. It covers core authentication workflows and data retrieval, though it could be slightly expanded for a more comprehensive eClass integration.

Completeness3/5

The tools cover authentication and course listing well, but there are notable gaps for typical eClass functionality such as accessing course content, assignments, grades, or announcements. This limits the server's ability to support full eClass workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers