Merge pull request #6622 from dot-RealityTest/add-obsidian-codex-mcp

Add Obsidian Codex MCP 🤖🤖🤖

README.md

@@ -1681,6 +1681,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [dodopayments/contextmcp](https://github.com/dodopayments/context-mcp) 📇 ☁️ 🏠 - Self-hosted MCP server that indexes documentation from various sources and serves it to AI Agents with semantic search.
 - [doobidoo/MCP-Context-Provider](https://github.com/doobidoo/MCP-Context-Provider) 📇 🏠 - Static server that provides persistent tool-specific context and rules for AI models
 - [doobidoo/mcp-memory-service](https://github.com/doobidoo/mcp-memory-service) 📇 🏠 - Universal memory service providing semantic search, persistent storage, and autonomous memory consolidation
+- [dot-RealityTest/obsidian-codex-mcp](https://github.com/dot-RealityTest/obsidian-codex-mcp) 🐍 🏠 🍎 🪟 🐧 - Local-first Obsidian vault MCP server for Codex, Claude Desktop, and other MCP clients. Works directly with markdown files, no Obsidian plugin, API key, cloud service, or running Obsidian app required. Includes read-only mode, backup-on-write, path isolation, and setup examples.
 - [DollhouseMCP/mcp-server](https://github.com/DollhouseMCP/mcp-server) [![DollhouseMCP MCP server](https://glama.ai/mcp/servers/DollhouseMCP/mcp-server/badge)](https://glama.ai/mcp/servers/DollhouseMCP/mcp-server) 📇 🏠 🍎 🪟 🐧 - One-line installable MCP server that adds reusable customization elements — personas, skills, templates, agents, memory, and ensembles (collected customization tools) — to any MCP Client application. Dynamic permissioning for safe AI operations, a robust validation architecture, versioning, and a public collection of shareable content. Install: `npx @dollhousemcp/mcp-server@latest --web`.
 - [DomDemetz/claude-soul](https://github.com/DomDemetz/claude-soul) [![DomDemetz/claude-soul MCP server](https://glama.ai/mcp/servers/DomDemetz/claude-soul/badges/score.svg)](https://glama.ai/mcp/servers/DomDemetz/claude-soul) 📇 🏠 🍎 🐧 - Self-improving learning engine for Claude Code. Extracts signals from every session (corrections, successes, confusion), runs periodic reflections, and evolves behavioral frameworks through evidence tiers (hypothesis → observed → validated). Frameworks that keep working get promoted, bad ones get retired. 9 MCP tools, automatic hooks, phase-adaptive learning. Single dependency, local-only. `npx claude-soul init --starter`
 - [edobusy/agenthold](https://github.com/edobusy/agenthold) [![agenthold MCP server](https://glama.ai/mcp/servers/edobusy/agenthold/badges/score.svg)](https://glama.ai/mcp/servers/edobusy/agenthold) 🐍 🏠 🍎 🪟 🐧 - Shared versioned state store with optimistic concurrency control for coordinating concurrent AI agents. SQLite-backed claim/release locks and append-only audit log.