57 skills found · Page 2 of 2
backblaze-labs / claude-skill-b2-cloud-storageClaude Skill for Backblaze B2 Cloud Storage management from the terminal. Manage buckets, list and search files, audit storage usage, detect stale or large objects, review security posture, and safely clean up data using natural language.
reposkein / reposkeinDeterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust, Go, Java, C#.
HaseebKhalid1507 / VelociRAGLightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
Alexey-N-Chernyshov / gramps-web-mcp-rsMCP server for Gramps Web genealogy API, written in Rust. Inspired by gramps-mcp — more tools, test coverage, smaller image, optional read-only mode.
akudo7 / kudosflowVisual workflow editor for building node-based AI agent workflows with drag-and-drop interface, A2A integration, and real-time execution
tobs-code / a-mem-mcp-serverA-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten
mshtawythug / second-brainLocal-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, no API keys); queryable by any AI agent through the built-in MCP server.
jcdreamjc / wudao-mcp63 read-only China A-share MCP tools for AI Agents: K-line, limit-up ladder, capital flow, Dragon Tiger List and post-market review.
CyranoB / web-foragerA search-and-fetch toolkit for AI agents, available as an MCP server and as standalone Agent Skills
patakuti / local-knowledge-rag-mcpA semantic search and retrieval system for local documents using vector embeddings. Powered by MCP (Model Context Protocol).
gourraguis / glasses-mcpGlasses MCP is a simple MCP server that lets your AI agent see and capture the web 👓
Intradyne / AnyLoom-AnythingLLM-Local-AI-agentic-DyTopo-swarmChatGPT-like AI that runs 100% locally on your hardware. No subscriptions, no cloud, complete privacy. Multi-agent swarm + 10 MCP tools + hybrid RAG vector DB + . Runs on one GPU (RTX 5090 recommended)
MarshallEriksen-Neura / ragcodeVerified, fully-local code context for AI agents. MCP-native. No cloud, no editor lock-in.
24601 / agent-deep-researchDeep research (CLI and agent skill) via the Gemini Interactions API. Automatic RAG grounding from local files (optional), cost estimation (--dry-run), adaptive polling, structured output, and agent onboarding. No Gemini CLI dependency.
tse-wei-chen / MCP-TRPG-GameAn advanced TRPG (Tabletop Role-Playing Game) server designed for automated, AI-driven adventures. This project leverages Large Language Models (LLMs) as the Keeper (KP), allowing the AI to lead, narrate, and manage the game, making every session dynamic and immersive.
ricard1406 / Little_MCPA simple yet powerful local AI Agent assistant that runs entirely on your machine. Option for remote LLM. Built for learning and deploy, Little MCP combines the power of open-source LLMs with advanced RAG that work with your personal documents.
alessandro9110 / Speech-To-Text-With-DatabricksAn end-to-end, scalable STT solution on Databricks that transcribes audio into structured text in Delta Lake, ready for analytics, search, and GenAI/RAG.
gupta29470 / codewalkAI-powered codebase onboarding tool — point it at any repo and ask questions about the code. Uses tree-sitter parsing, RAG, and local LLMs.
timoncool / telegram-api-mcpUltimate Telegram Bot API MCP server — full v9.6 coverage, meta-mode, rate limiting, circuit breaker. TypeScript.
leonardommello / copilot-mcp-toolMCP server that enables AI assistants to interact with Github Copilot cli, leveraging copilot massive token window for large file analysis and codebase understanding
rwnalds / engramSelf-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
chirag127 / mdv-mcpLocal, private MCP server for a markdown/Obsidian vault - NVIDIA nemotron-3-embed-1b semantic search, pure-JS int8 vector store, read/write/delete tools. Local only, never published to npm.
T-NhanNguyen / graphRAG-LlamaIndexgraphRAG agent harness tool
Haruto-Sa / mdExport"version": "0.0.0", "scripts": { "dev": "next dev", "dev:mcp": "concurrently -k -s first \"uv tool run arxiv-mcp-server --port 8000 --storage-path ./arxiv-default-paper\" \"npx -y markitdown-mcp-npx --http --host 127.0.0.1 --port 8010\"", "build": "next build", "start": "next start", "lint": "next l…
tenthdragon / roove-bi"backfill:scalev-header-financials": "tsx scripts/backfill-scalev-header-financials.ts", "backfill:marketplace-intake-shipping": "tsx scripts/backfill-marketplace-intake-shipping.ts", "backfill:marketplace-tracking": "tsx scripts/ops/backfill-marketplace-tracking.ts", "check:mcp": "npm --prefix mcp-…
TransAdvocacyAndComplaintCollective / fact_index_tacc"test:e2e": "node --test --test-concurrency=1 tests/e2e/*.e2e.test.mjs", "test:e2e:coverage": "rm -rf .coverage/e2e && mkdir -p .coverage/e2e/v8 && NODE_OPTIONS= NODE_V8_COVERAGE=.coverage/e2e/v8 node --test --test-concurrency=1 tests/e2e/*.e2e.test.mjs && pnpm dlx c8 report --temp-directory .covera…
zakirkun / guardian-cliGuardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.
