tbank-edu-mcp
MCP server that connects AI assistants to T-Bank Education, enabling access to courses, timetable, deadlines, and user profile via tools like get_timetable, get_my_courses, and get_deadlines.
README
tbank-edu-mcp
MCP server for edu.tbank.ru — connect your AI assistant to T-Bank Education.
Built with TypeScript on Cloudflare Workers. Uses the Model Context Protocol so Claude Desktop, Cursor, and other MCP clients can access your courses, timetable, and deadlines.
Python API client: mollyvita/tbank-edu-api
What It Does
| Tool | What you get |
|---|---|
get_timetable |
Upcoming events — meetups, deadlines, course starts |
get_my_courses |
Your enrolled courses and activities |
get_deadlines |
Deadlines with progress tracking |
get_completed_activities |
Finished courses |
search_catalogue |
Search all available courses |
get_selections |
Exam selections and applications |
get_notifications |
Notification count |
get_favorites |
Your favorited courses |
get_streams |
Available programs and streams |
get_user_info |
Your profile — name, email, roles |
login / logout / refresh_session |
Session management |
Quick Start
1. Deploy
Click the button above, or deploy manually:
git clone https://github.com/mollyvita/tbank-edu-mcp.git
cd tbank-edu-mcp
npm install
npx wrangler login
npm run deploy
2. Add Your Credentials
npx wrangler secret put TBANK_EMAIL
npx wrangler secret put TBANK_PASSWORD
This lets the server auto-login. Without secrets, you'd call the login tool manually each session.
3. Connect Your AI Client
Add to Claude Desktop or Cursor MCP config:
{
"mcpServers": {
"tbank-edu": {
"url": "https://tbank-edu-mcp.<your-subdomain>.workers.dev/mcp"
}
}
}
That's it. Ask your AI about your courses, deadlines, or timetable.
Local Dev
npm install
npm run dev # http://localhost:8787/mcp
npm run typecheck # tsc --noEmit
For local testing, point your MCP client at http://localhost:8787/mcp.
Environment Variables
| Variable | Default | Description |
|---|---|---|
TBANK_BASE_URL |
https://edu.tbank.ru |
API base URL |
TBANK_EMAIL |
— | Auto-login email (Cloudflare secret) |
TBANK_PASSWORD |
— | Auto-login password (Cloudflare secret) |
How It Works
src/
├── index.ts # Worker entry point + routing
├── api-client.ts # HTTP client — handles CSRF tokens + cookies
└── tools.ts # MCP tool definitions
- Uses
@modelcontextprotocol/sdkwith Streamable HTTP transport (SSE) - CSRF token extracted from
x-edu-csrf-tokenresponse header - Auth via JWT cookies from
/api/auth/signin/v8 - Stateless per request — authenticates fresh using stored secrets
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.