MCP servers and skills: search, filter by where they run, and compare.
TOON-Native Auto-Embedding & RAG Toolkit for MariaDB | Judges' Guide & live demo: https://mariadb-hackathon-my-2026.github.io/seamless-rag/
SkillApache-2.0★ 3Few starsNo key
🥈 2nd Place @ MariaDB Hackathon Malaysia 2026 — TOON-Native Auto-Embedding & RAG Toolkit for MariaDB | Docs & Judges' Guide: https://mariadb-hackathon-my-2026.github.io/seamless-rag/
SkillApache-2.0★ 2Few starsNo key
Agentic Runtime Extensible Server. A composable AI agent runtime in Rust based on the Cordis framework
SkillMIT★ 18No key
Multi-query web search via SearXNG + dynamic page scraping with browser support + TOON encoding/decoding for LLM optimization
PythonMITFew starsNo key
MCP server for the Disney Lorcana TCG — card search, deck validation, deck stats, and Dreamborn/Pixelborn deck import/export for Claude and other MCP clients.
PythonMIT★ 1Few starsNo key
A production-grade agentic chatbot server built in Rust with multi-provider LLM support, tool calling, RAG, MCP integration, and advanced research capabilities
SkillMIT★ 2Few starsNo key
Chomper - Chomp through any document. MCP server for parsing 36+ file formats with semantic chunking & TOON token optimization for Claude and AI systems.
PythonMITFew starsNo key
An AXI (Agent eXperience Interface) for Notion — a token-efficient CLI for AI agents to search, read, and write Notion pages & databases.
SkillMIT★ 10No key
MCP multi-utility server with libSQL storage - provides key-val, vector-store, RAG, embeddings, and more
GoMIT★ 1Few starsNo key
Token-efficient knowledge base converter for AI Agents. Converts PDF, DOCX, & MD to TOON/YAML format.
SkillMITFew starsNo key
Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.
PythonBSD-3-Clause★ 204No key
Agent skill that writes ATS-friendly software engineer resumes as real `.docx` and `.pdf` files, tailored to a job description. Keeps a persistent candidate profile that grows across sessions and trac
SkillMITFew starsNo key
Give LLM agents 2 meta-tools instead of a 30k-token tool catalog - hierarchical, search-first tool discovery with an active tool request, hybrid retrieval, response filtering and code mode. Works with
SkillMITFew starsNo key
Who stands behind it
