wirux

πŸ“ Markdown Vault MCP Server

Community wirux
Updated

Headless semantic MCP server for Obsidian, Logseq, Dendron & any markdown vault. AST-based surgical editing, hybrid vector + TF-IDF search, zero-setup local embeddings β€” no app or plugins required. Stdio & SSE transport, Docker-ready.

πŸ“ Markdown Vault MCP Server

Headless semantic MCP server for Obsidian, Logseq, Dendron, Foam, and any folder of markdown files.

npm install and point it at a folder. Hybrid search, AST editing, zero-config embeddings. No app, no plugins, no API keys.

CI / ReleasePR Checknpm versionDockerLicense: MITTypeScriptNode.jsTests

πŸ’‘ Why this server?

TL;DR β€” One npx command. No running app. No plugins. No vector DB. Semantic search works out of the box.

Differentiator Details
🚫 No app or plugins required Most Obsidian MCP servers (mcp-obsidian, obsidian-mcp-server) need Obsidian running with the Local REST API plugin. This server reads and writes .md files directly β€” point it at a folder and go.
🧠 Built-in semantic search, zero setup Hybrid search: cosine-similarity vectors + TF-IDF + word proximity. Local embeddings (@huggingface/transformers, all-MiniLM-L6-v2, 384d) download on first run. No API keys, no external services. Ollama optional for higher quality.
πŸ”¬ Surgical AST-based editing remark AST pipeline patches specific headings or block IDs without touching the rest of the file. Freeform line-range & string replace as fallback. Levenshtein fuzzy matching handles LLM typos.
πŸ”“ Tool-agnostic Obsidian vaults, Logseq graphs, Dendron workspaces, Foam, or any plain folder of .md files. If it's markdown, it works.
πŸ“¦ Single package, no infrastructure Unlike Python alternatives that need ChromaDB or other vector stores, everything runs in one Node.js process. npx @wirux/mcp-markdown-vault and you're running. Docker image available.

πŸ’Ž Obsidian Β· πŸ““ Logseq Β· 🌳 Dendron Β· 🫧 Foam Β· πŸ“‚ Any .md folder

✨ Features

Feature Description
πŸ—‚οΈ Headless vault ops Read, create, update, edit, delete .md notes with strict path traversal protection
πŸ“‘ Read by heading Read a single section by heading title β€” returns only content under that heading (up to the next same-level heading), saving context window space
πŸ“¦ Bulk read Read multiple files and/or heading-scoped sections in a single call β€” reduces MCP round-trips with per-item fault tolerance
πŸ”¬ Surgical editing AST-based patching targets specific headings or block IDs β€” never overwrites the whole file
πŸ” Fragment retrieval Heading-aware chunking + TF-IDF + proximity scoring returns only relevant sections
πŸ“‚ Scoped search Optional directory filter for global_search and semantic_search β€” restrict results to specific folders to reduce noise
🧠 Semantic search Hybrid vector + lexical search with background auto-indexing
⚑ Zero-setup embeddings Built-in local embeddings via @huggingface/transformers β€” Ollama optional
πŸ”„ Workflow tracking Petri net state machine with contextual LLM hints
🌐 Dual transport Stdio (single client) or SSE over HTTP (multi-client, Docker-friendly)
✏️ Freeform editing Line-range replacement and string find/replace as AST fallback
🏷️ Frontmatter management AST-based read and update of YAML frontmatter β€” safely manage tags, statuses, and metadata without corrupting file structure
πŸ‘€ Dry-run / diff preview Preview any edit operation as a unified diff without saving β€” set dryRun=true on any edit action
πŸ“ Templating / scaffolding Create new notes from template files with {{variable}} placeholder injection β€” refuses to overwrite existing files
πŸ—ΊοΈ Vault overview Structural map of the vault β€” total file count, recursive folder tree with file counts and last modification dates per folder
πŸ“¦ Batch edit Apply multiple edit operations in a single call β€” sequential execution, stops on first error, supports dryRun, max 50 ops
πŸ”— Backlinks index Find all notes linking to a given path β€” supports wikilinks and markdown links with line numbers and context snippets
🎯 Typo resilience Levenshtein-based fuzzy matching for edit operations

πŸ› οΈ MCP Tools

Tool Actions Description
πŸ“ vault list read create update delete stat create_from_template Full CRUD for vault notes + template scaffolding
✏️ edit append prepend replace line_replace string_replace frontmatter_set batch AST-based patching + freeform fallback + frontmatter update + batch edit (supports dryRun diff preview)
πŸ‘οΈ view search global_search semantic_search outline read frontmatter_get bulk_read backlinks Fragment retrieval, cross-vault search, hybrid semantic search, read by heading, frontmatter read, bulk read, backlinks
πŸ”„ workflow status transition history reset Petri net state machine control
βš™οΈ system status reindex overview Server health, indexing info, vault structure overview

All tool responses include contextual hints based on the current workflow state.

πŸš€ Quick Start

Prerequisites

πŸ“¦ Install from NPM

npm install -g @wirux/mcp-markdown-vault

Then run directly:

VAULT_PATH=/path/to/your/vault markdown-vault-mcp

πŸ”Œ MCP Client Configuration

Add to your MCP client config (e.g. Claude Desktop, Claude Code):

{
  "mcpServers": {
    "markdown-vault": {
      "command": "npx",
      "args": ["-y", "@wirux/mcp-markdown-vault"],
      "env": {
        "VAULT_PATH": "/path/to/your/vault"
      }
    }
  }
}

npx -y auto-installs the package if not already present β€” no global install needed.

Try it in the browser: You can test this server directly at β€” no local install required.

🐳 Docker

Pull the pre-built multi-arch image from GitHub Container Registry:

docker pull ghcr.io/wirux/mcp-markdown-vault:latest

Or use Docker Compose:

docker compose up

Edit docker-compose.yml to point at your markdown vault directory. The default compose file uses SSE transport on port 3000.

πŸ› οΈ Development (from source)

git clone https://github.com/Wirux/mcp-obsidian.git
cd mcp-obsidian
npm install
npm run build
VAULT_PATH=/path/to/your/vault node dist/index.js

🌐 Transport Modes

Mode Use case How it works
πŸ“‘ stdio (default) Single-client desktop apps (Claude Desktop) Reads/writes stdin/stdout; 1:1 connection
🌊 sse Multi-client setups (Docker, Claude Code) HTTP server with SSE streams; one connection per client

SSE starts an HTTP server on PORT (default 3000):

  • GET /sse β€” establishes an SSE stream (one per client)
  • POST /messages?sessionId=... β€” receives JSON-RPC messages
MCP_TRANSPORT_TYPE=sse PORT=3000 VAULT_PATH=/path/to/vault npx @wirux/mcp-markdown-vault

Each SSE client gets its own workflow state. Shared resources (vault, vector index, embedder) are reused across all connections.

🧠 Embedding Providers

The server selects an embedding provider automatically:

OLLAMA_URL set? Ollama reachable? Provider used
❌ No β€” 🏠 Local (@huggingface/transformers, all-MiniLM-L6-v2, 384d)
βœ… Yes βœ… Yes πŸ¦™ Ollama (nomic-embed-text, 768d)
βœ… Yes ❌ No 🏠 Local (fallback with warning)

No configuration needed for local embeddings β€” the model downloads on first use and is cached automatically.

βš™οΈ Configuration

Variable Default Description
VAULT_PATH /vault Markdown vault directory
MCP_TRANSPORT_TYPE stdio stdio (single client) or sse (multi-client HTTP)
PORT 3000 HTTP port (SSE mode only)
OLLAMA_URL (unset) Set to enable Ollama embeddings
OLLAMA_MODEL nomic-embed-text Ollama embedding model name
OLLAMA_DIMENSIONS 768 Ollama embedding vector dimensions

πŸ—οΈ Architecture

Clean Architecture with strict layer separation:

src/
β”œβ”€β”€ domain/           πŸ”· Errors, interfaces (ports), value objects
β”œβ”€β”€ use-cases/        πŸ”Ά Business logic (AST, chunking, search, workflow)
β”œβ”€β”€ infrastructure/   🟒 Adapters (file system, Ollama, vector store)
└── presentation/     🟣 MCP tool bindings, transport layer (stdio/SSE)

See CLAUDE.md for detailed architecture docs and CHANGELOG.md for implementation history.

🚒 CI/CD & Release

Fully automated via GitHub Actions and Semantic Release:

Workflow Trigger What it does
PR Check Pull request to main Lint β†’ Build β†’ Test
Release Push to main Lint β†’ Test β†’ Semantic Release (NPM + GitHub Release) β†’ Docker build & push to ghcr.io

πŸ§ͺ Testing

318 tests across 31 files, written test-first (TDD).

npm test                                          # Run all tests
npx vitest run src/use-cases/ast-patcher.test.ts  # Single file
npm run test:watch                                # Watch mode
npm run test:coverage                             # Coverage report

Tests use real temp directories for file system operations and in-memory MCP transport for integration tests. No external services required.

πŸ”’ Security

  • πŸ›‘οΈ All file paths validated through SafePath value object before any I/O
  • 🚫 Blocks path traversal: ../, URL-encoded (%2e%2e), double-encoded (%252e), backslash, null bytes
  • ✍️ Atomic file writes (temp file + rename) prevent partial writes
  • πŸ‘€ Docker container runs as non-root user

πŸ“„ License

MIT

MCP Server Β· Populars

MCP Server Β· New

    remete618

    widemem.ai

    Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

    Community remete618
    Ruya-AI

    Cozempic

    Context cleaning for Claude Code β€” prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

    Community Ruya-AI
    KuvopLLC

    better bear

    MCP Server

    Community KuvopLLC
    tradesdontlie

    TradingView MCP Bridge

    AI-assisted TradingView chart analysis β€” connect Claude Code to your TradingView Desktop for personal workflow automation

    Community tradesdontlie
    us

    fastCRW β€” Open Source Web Scraping API for AI Agents

    Fast, lightweight Firecrawl alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/v1/scrape, /v1/crawl, /v1/search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

    Community us