Independent researcher in neuro-symbolic AI and knowledge-graph question answering. I also build developer tools and MCP infrastructure.
- TACET (Latin: it is silent) — Cost-Amortised Knowledge-Graph Question Answering via Self-Distilling Neuro-Symbolic Cascades. A three-tier cascade — a sound Datalog engine, a calibrated ComplEx link predictor, and an LLM teacher — with an online distillation loop that mines teacher answers into auditable Horn rules, amortising LLM cost while every symbolic answer ships a replayable proof tree. code · preprint doi:10.5281/zenodo.20666554.
/plugin marketplace add n24q02m/claude-pluginsThen /plugin install <name>@n24q02m-plugins. All 8 MCP servers in one marketplace.
| Server | Description | Agent Setup | Runtime |
|---|---|---|---|
| wet-mcp | Web search, content extraction, and documentation indexing | Guide | uvx wet-mcp |
| mnemo-mcp | Persistent AI memory with hybrid search and cross-machine sync | Guide | uvx mnemo-mcp |
| better-notion-mcp | Markdown-first Notion API with 10 composite tools | Guide | npx @n24q02m/better-notion-mcp |
| better-email-mcp | Email (IMAP/SMTP) with multi-account and auto-discovery | Guide | npx @n24q02m/better-email-mcp |
| better-godot-mcp | Godot Engine 4.x with 17 composite tools for scenes, scripts, and shaders | Guide | npx @n24q02m/better-godot-mcp |
| better-telegram-mcp | Telegram dual-mode (Bot API + MTProto) with 6 composite tools | Guide | uvx better-telegram-mcp |
| better-code-review-graph | Knowledge graph for token-efficient code reviews | Guide | uvx better-code-review-graph |
| imagine-mcp | Image and video understanding + generation across Gemini, OpenAI, and Grok | Guide | uvx imagine-mcp |
Setup any server: Copy the Agent Setup guide link and send it to your AI agent with "Please set up this MCP server for me."
Shared principles across the MCP servers, built on the mcp-core foundation. The credential-handling ones (1, 6, 8) apply to every server that talks to an upstream account; better-godot-mcp is the exception -- it runs locally with no credentials, so it skips the relay and auth layers entirely.
- Zero-Knowledge Relay -- E2E encryption (ECDH P-256 + AES-256-GCM). Relay server never sees plaintext credentials. URL fragment secrets stay client-side per RFC 3986.
- Composite Tool Pattern -- One tool per domain with action dispatch: 4-17 tools per server instead of dozens of thin endpoints, saving LLM context tokens.
- 3-Tier Token Optimization -- Compact descriptions (always loaded), help docs (on demand), and MCP resources (deep reference) keep the always-on tool schema small.
- Tool Annotations --
readOnlyHint,destructiveHint,idempotentHint,openWorldHintmetadata so the LLM knows tool behavior before calling. - Security Defense-in-Depth -- SSRF prevention, path-traversal containment, prompt-injection (XPIA) boundary tags around untrusted content, and error sanitization.
- Multi-User HTTP Mode -- Stateless DCR (HMAC-SHA256), per-user session isolation, AES-256-GCM credential encryption at rest, OAuth 2.1 + PKCE S256.
- Degraded Mode -- Server always starts, even without credentials. Help and config tools work. Data tools return setup instructions instead of crashing.
- Zero-Config Relay Setup -- Auto-open browser, user enters credentials, server receives config via encrypted relay, saves to local config.enc.
| Package | Description | Install |
|---|---|---|
| mcp-core | Streamable HTTP transport, OAuth 2.1, browser-based credential setup, lifecycle, and a shared embedding daemon | npm i @n24q02m/mcp-core / pip install n24q02m-mcp-core |
| qwen3-embed | Lightweight ONNX inference for Qwen3 embedding and reranking models | pip install qwen3-embed |
| web-core | Shared web infrastructure: SSRF-safe HTTP, SearXNG search, multi-strategy scraping, stealth browsers | pip install n24q02m-web-core |
| Tool | Description | Install |
|---|---|---|
| jules-task-archiver | Chrome Extension to bulk-archive completed Jules tasks | Download zip |
| skret | Cloud-provider secret manager CLI with Doppler/Infisical-grade DX. Zero lock-in, zero server. | brew install n24q02m/tap/skret |
- KnowledgePrism -- Chat with your knowledge. Ingest anything (URL, PDF, EPUB, DOCX, CBZ, audio, video, image, text) into a persistent per-project knowledge graph, then produce any format (translation, brief, podcast, slide deck, mindmap, quiz, export). One chat-first agent plans compound requests as a typed capability DAG; ProjectKG is the auto-maintained spine, not a feature. klprism.com
- Aiora -- A health and environment companion for daily wellness. getaiora.com
- LinguaSense -- Realtime knowledge transfer from any screen or microphone. Desktop + mobile. (coming)
- Akasha / GWM -- Research: one graph-centric model with an LLM SOTA teacher, autonomous continuous learning.