xiaoya-teacher-mcp-server

This package provides a Python-based MCP server for “Xiaoya” (小雅) education management, exposing tools for teacher-oriented workflows such as course resource management, question/quiz creation and management, classroom & attendance (签到) queries, and task/assignment + grading workflows. It supports multiple MCP transports (stdio by default, plus SSE and streamable HTTP). Authentication to the upstream service can be done either via account/password (with server-side token caching and automatic re-login) or via a provided Bearer token.

Evaluated Apr 04, 2026 (17d ago)
Homepage ↗ Repo ↗ Ai Ml mcp education teacher-tools questions resources attendance grading python
⚙ Agent Friendliness
61
/ 100
Can an agent use this?
🔒 Security
49
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
80
Documentation
65
Error Messages
0
Auth Simplicity
70
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
60
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
40

HTTPS/TLS enforcement is not explicitly stated in the README (remote transports show HTTP examples). Authentication supports account/password and bearer tokens; account/password mode implies token caching, and bearer mode does not auto-refresh. No evidence of fine-grained authorization scopes per tool is documented. Secrets handling details (e.g., whether credentials/tokens are ever logged) are not specified, so this score is conservative. Dependency list is small and bounded versions are suggested, but no vulnerability posture is documented.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
30
Error Recovery
55
AF Security Reliability

Best When

You want an MCP integration path for an AI assistant (e.g., Claude Desktop/Cursor) to automate teacher management tasks, and you can run the MCP server locally or in a controlled network with the specified authentication approach.

Avoid When

You need fine-grained authorization controls per tool/user, strong secrets-handling guarantees (beyond what’s described), or you can’t tolerate beta-stage software with limited evidence of robustness/testing.

Use Cases

  • Integrate an AI assistant with Xiaoya education management via MCP tools
  • Create and manage question banks (multiple question types, rich text, batch operations)
  • Manage course resources and files (create/update/delete, download, markdown conversion)
  • Query classroom info and attendance/签到 statistics
  • Publish tasks/quizzes, review submissions, and record grades/feedback

Not For

  • Production-grade classroom systems requiring a documented SLA, rigorous operational guarantees, and comprehensive security hardening
  • Environments where you cannot securely handle account/password or tokens (especially over HTTP)
  • Use cases that need a stable, documented public REST/GraphQL/OpenAPI API for long-term machine integration

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Account/password (auto login with token caching; automatic re-login on expiry for in-flight requests) Bearer token (direct authentication; no auto re-login) HTTP headers for remote transport: X-XIAOYA-ACCOUNT/X-XIAOYA-PASSWORD or Authorization: Bearer <token>
OAuth: No Scopes: No

No OAuth is described. Authentication is described at the MCP transport boundary using environment variables for stdio and HTTP headers for remote transports. Fine-grained scopes/permissions are not documented.

Pricing

Free tier: No
Requires CC: No

No pricing information is provided; this appears to be a self-hosted open-source Python package (MIT).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Documented

Known Gotchas

  • Token-expiry handling differs by auth mode: account/password mode may auto re-login and retry once; Bearer-token mode requires the caller to refresh and retry.
  • Remote HTTP transports accept credentials via headers; ensure clients are configured to avoid leaking credentials in logs.
  • Default behavior returns summaries to save tokens; requesting full details may increase response size and latency.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for xiaoya-teacher-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered