findclass-mcp
Local stdio MCP adapter exposing permission-filtered tools for FindClass backend operations, including order/refund/settlement/slot management, record search, and coupon grants.
README
FindClass MCP adapter
The adapter is local stdio only. It forwards the 20 bounded tools to the authenticated backend workflow API.
Trade and fulfillment tools cover permission-filtered order/refund/settlement/slot reads, order rescheduling, fulfillment recording, and tutor-slot create/close. Payment callbacks are never MCP tools. Refund review remains in the admin UI because it requires the existing dedicated refund permission and a fresh TOTP; settlement writes remain in the finance workflow. Record search and detail lookup cover content, external applications, orders, refunds, settlements, and tutor slots; every result is filtered by the live permissions of the account that owns the MCP token. Coupon grants freeze at most 100 selected users and issue one coupon per user; larger or multi-coupon grants stay in the admin UI.
{
"mcpServers": {
"findclass": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/findclass-mcp/server.py"],
"env": {
"FINDCLASS_BASE_URL": "https://your-findclass-backend",
"FINDCLASS_MCP_TOKEN": "set-in-the-client-secret-store"
}
}
}
}
Install from the hash lock:
uv venv --python 3.14 .venv
uv pip install --python .venv/bin/python --require-hashes -r requirements.lock
.venv/bin/python -m unittest -v test_server.py
Or run ./install-mcp-adapter.sh; it installs the same hash-locked adapter without writing a token.
The token is reveal-once and must not be written into this repository or ordinary client logs.
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.