"Bun" matching MCP servers:

Local-first markdown vault with a built-in MCP server (streamable HTTP). 16 tools and 2 resources for Claude Code / Desktop / Cursor: read/write/search plus context_for_query, find_orphans, weekly_digest, compare_notes, semantic_outline. Per-folder agent permissions, LanceDB vectors, local Xenova ONNX embedder swappable to Ollama. Single Bun binary. AGPL.

A template for building Model Context Protocol servers using Elysia and Bun runtime, enabling LLM clients like Claude Desktop and Cody to access custom tools, prompts, and data resources.

Provides AI agents with persistent memory and knowledge management through a comprehensive knowledge graph platform. Enables storing, searching, and managing entities, relationships, and observations with advanced features like trending analysis and smart ranking.

An MCP server that finds Sun Tzu quotes for workplace situations, matching plain-language descriptions to verses from The Art of War with chapter citations, plus tools for themes, random quotes, and PNG quote cards.

A local MCP server that integrates with Claude Desktop, enabling RAG capabilities to provide Claude with up-to-date private information from custom LlamaCloud indices.

Enables AI assistants to build and query temporally-aware knowledge graphs from conversations and data. Supports adding episodes, searching entities and facts, and maintaining persistent memory across interactions.

Enables agents to search indexed documents and GitHub repository code through stdio-exposed tools, returning relevant evidence for grounded answers and code reviews.

A MCP server connecting to a managed index on LlamaCloud. This is a TypeScript-based MCP server that implements a connection to a managed index on LlamaCloud.

Enables indexing and searching Obsidian notes via MCP, using Cloudflare's serverless platform for cost-effective vector embeddings and AI-powered search.

Enables identification of BSN SKU/material and real-time inventory availability through natural language queries and vector search.

MCP server that provides live Odoo documentation (v15.0–v19.0+) in clean Markdown, enabling AI assistants to search, fetch, and export official Odoo user and developer docs.

Enables agents to discover, evaluate, and serve task-specialist models (embeddings, reranking, classification, extraction) with OpenAI-compatible endpoints and MCP tools for routing, embedding, reranking, and extraction.

A meta-MCP server that acts as a universal gateway, allowing users to discover and execute tools from thousands of other MCP servers through semantic search. It dynamically loads servers on demand and provides standardized functions for searching, discovering, and running tools across the entire MCP ecosystem.