AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Learnbot Mcp

mcp-sandraschi-learnbot-mcp · by sandraschi

AI chatbot orchestrator — personas, safety-guarded conversations, TTS, VRM avatar, structured language lessons (any language, deep Japanese/JLPT)

— No reviews yet
0 installs
25 views
0.0% view→install

Install

$ agentstack add mcp-sandraschi-learnbot-mcp

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-sandraschi-learnbot-mcp)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Learnbot Mcp? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

learnbot-mcp

AI chatbot orchestrator — personas, safety-guarded conversations, spoken TTS, an interactive VRM avatar, and structured language lessons (any language, with deep Japanese/JLPT support) — all logged and auditable.

Preview

The webapp is a 12-page control panel (Personas, Chat, Avatar, Lessons, Japanese, Safety, Audit, Compliance, Voices, Demos, Help) - this is the human side of what the MCP tools drive for agents.

| Dashboard | Chat | Japanese | |-----------|------|----------| | | | |

Captured 2026-08-02 by the CUA-NSIS smoke test against the installed app (12 pages, live API data - see docs/screenshots/cua-*.png).

Features

  • Personas — define AI characters with backstory, voice, languages, skills, and scheduled proactive messages
  • Safety-guarded chat — topic blocking, rate limiting, PII redaction, full conversation audit log
  • Interactive VRM avatar (/avatar) — three.js viewer with orbit/zoom, facial expressions, auto-blink, look-at-cursor; served from GET /api/avatar.vrm
  • Language-agnostic lessons — AI-generated lesson plans, spaced-repetition vocab quizzes (SM-2), grammar check, graded readers; every tool takes source_lang/target_lang, not just Japanese
  • Deep Japanese/JLPT toolset (/japanese) — bundled kanji, JMdict, JLPT vocab (N5–N1), and example-sentence lookups run on local SQLite, no external service required — plus 11 linked practice games (kanji drills, flashcards, karuta, listening) from a separate optional ai-games-collection
  • Multi-platform output — speak via TTS (Gemini prosody via speech-mcp, falls back to Windows SAPI5), or send to Discord/Resonite bridges
  • 35 MCP tools across personas, conversations, lessons, language tools, safety, and audit — see [docs/TOOLS.md](docs/TOOLS.md)

Quick Install

Drag learnbot-mcp-{version}.mcpb onto Claude Desktop.

See [INSTALL.md](INSTALL.md) for all install paths (drag-and-drop, mcpb CLI, manual config, dev mode) — manual config is what's actually verified working today.

What You Can Do

> "Create a persona named Miko who teaches Japanese, start a chat with her, and quiz me on N5 vocabulary."

> "Show me the VRM avatar with a happy expression and have her say hello."

> "Generate a beginner Spanish lesson on ordering food, then run it in a new conversation."

Documentation

| Doc | Contents | |-----|----------| | [Installation](INSTALL.md) | All install methods, prerequisites | | [Configuration](docs/CONFIGURATION.md) | Env vars, config options | | [Tool Reference](docs/TOOLS.md) | All 35 MCP tools | | [Development](docs/DEVELOPMENT.md) | Contributing, local setup, tests | | [Troubleshooting](docs/TROUBLESHOOTING.md) | Common issues | | [Japanese Learning Guide](docs/JAPANESELEARNING.md) | Full-spectrum Japanese learning — four skills, phased workflow, JLPT comparison | | [Distance Learning](docs/DISTANCELEARNING.md) | Paired with classroom-mcp — courses, teaching agents, courseware | | [Arabic → German Integration](docs/INTEGRATION_AR.md) | دليل بالعربية — learn German for Austrian daily life | | [Chatbot Ethics](docs/chatbot-ethics.md) | Addiction, regulation, pseudohuman dynamics |

Requirements

  • Claude Desktop (or another MCP client) + Python 3.12+
  • Node.js, for the webapp
  • Windows for the TTS SAPI5 fallback; core features are OS-agnostic
  • Optional: local-llm-mcp or Ollama, for AI-generated lessons/grammar-check/reading passages — the dictionary/kanji/JLPT tools need no LLM at all

License

MIT — see [LICENSE](LICENSE).

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.