What can you do with this server?

mcp-markdown-vault is a headless MCP server for reading, writing, searching, and managing markdown vaults (Obsidian, Logseq, Dendron, Foam, or any folder of .md files) — no app or API keys required. Vault Management — Full CRUD on notes (list, read, create, update, delete, stat), plus scaffold new notes from templates with {{variable}} placeholder injection. Surgical Editing — AST-based append/prepend/replace targeting specific headings or block IDs with fuzzy matching, freeform line-range and string replacements, YAML frontmatter updates, batch edits (up to 50 operations), and dry-run diff previews. Search & Retrieval — Hybrid semantic search (vector + lexical, zero-setup local embeddings with optional Ollama), global keyword search, single-file fragment retrieval (TF-IDF + proximity), bulk read of multiple files/sections, heading-scoped section reads, note outline view, frontmatter reads, and backlinks (wikilinks + markdown links with line context) — all optionally scoped to a directory. Workflow Tracking — Petri net state machine with status checks, transition firing, history view, and reset, plus contextual LLM hints for agent workflows. System Administration — Server health/status, full vault reindexing, and structural vault overview (folder tree, file counts, modification dates). Transport & Security — Dual transport modes (stdio for single client, SSE over HTTP for multi-client/Docker), path traversal protection, atomic file writes, and safe path validation.

Which integrations are available for this server?

Provides Docker container deployment option with multi-arch support via GitHub Container Registry, enabling SSE transport mode for multi-client setups and containerized vault operations. Enables MCP server capabilities for Logseq graphs, offering markdown file operations, semantic search, fragment retrieval, and surgical editing for Logseq's knowledge base structure. Provides headless semantic MCP server functionality for Obsidian vaults, enabling direct read/write operations, surgical AST-based editing, semantic search, and workflow tracking without requiring the Obsidian app or plugins. Supports optional integration with Ollama for higher-quality embeddings in semantic search functionality, using models like nomic-embed-text for improved vector search results.

de en es ja ko ru zh

mcp-markdown-vault

by wirux

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

📁 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 / Release PR Check npm version Docker License: MIT TypeScript Node.js Tests mcp-markdown-vault MCP server

Markdown Vault MCP Server Demo

💡 Why this server?

TL;DR — 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 — 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.
🔬	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.
🔓	Tool-agnostic	Obsidian vaults, Logseq graphs, Dendron workspaces, Foam, or any plain folder of `.md` files. If it's markdown, it works.
📦	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.

💎 Obsidian · 📓 Logseq · 🌳 Dendron · 🫧 Foam · 📂 Any .md folder

✨ Features

	Feature	Description
🗂️	Headless vault ops	Read, create, update, edit, delete `.md` notes with strict path traversal protection
📑	Read by heading	Read a single section by heading title — returns only content under that heading (up to the next same-level heading), saving context window space
📦	Bulk read	Read multiple files and/or heading-scoped sections in a single call — reduces MCP round-trips with per-item fault tolerance
🔬	Surgical editing	AST-based patching targets specific headings or block IDs — never overwrites the whole file
🔍	Fragment retrieval	Heading-aware chunking + TF-IDF + proximity scoring returns only relevant sections
📂	Scoped search	Optional directory filter for `global_search` and `semantic_search` — 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` — Ollama optional
🔄	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 — safely manage tags, statuses, and metadata without corrupting file structure
👀	Dry-run / diff preview	Preview any edit operation as a unified diff without saving — set `dryRun=true` on any edit action
📝	Templating / scaffolding	Create new notes from template files with `{{variable}}` placeholder injection — refuses to overwrite existing files
🗺️	Vault overview	Structural map of the vault — total file count, recursive folder tree with file counts and last modification dates per folder
📦	Batch edit	Apply multiple edit operations in a single call — sequential execution, stops on first error, supports `dryRun`, max 50 ops
🔗	Backlinks index	Find all notes linking to a given path — supports wikilinks and markdown links with line numbers and context snippets
🎯	Typo resilience	Levenshtein-based fuzzy matching for edit operations

🛠️ MCP Tools

Tool	Actions	Description
📁 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)
👁️ 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
🔄 workflow	`status` `transition` `history` `reset`	Petri net state machine control
⚙️ system	`status` `reindex` `overview`	Server health, indexing info, vault structure overview

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

🚀 Quick Start

Prerequisites

Node.js >= 22
(Optional) Ollama for higher-quality embeddings

📦 Install from NPM

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

Then run directly:

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

🔌 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 — no global install needed.

Try it in the browser: You can test this server directly at Glama Inspector — 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.

🛠️ 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
📡 `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 — establishes an SSE stream (one per client)
POST /messages?sessionId=... — 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	—	🏠 Local (`@huggingface/transformers`, `all-MiniLM-L6-v2`, 384d)
✅ Yes	✅ Yes	🦙 Ollama (`nomic-embed-text`, 768d)
✅ Yes	❌ No	🏠 Local (fallback with warning)

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

⚙️ Configuration

Variable	Default	Description
`VAULT_PATH`	`/vault`	Markdown vault directory
`VAULT_CONTEXT`	`general markdown notes vault`	One-line description of vault scope; surfaced to connected agents via MCP instructions and tool descriptions
`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
`VECTOR_STORE_URL`	(unset)	Set to use Qdrant (e.g. `http://localhost:6333`). If unset, local persisted flat store is used.
`VECTOR_STORE_RESET`	`false`	Set to `true` to auto-delete a mismatched vector index on startup and rebuild from scratch.

Note: When using the default local vector store, a .markdown_vault_mcp directory will be created in your vault. It's recommended to add this directory to your .gitignore.

🏗️ Architecture

Clean Architecture with strict layer separation:

src/
├── domain/           🔷 Errors, interfaces (ports), value objects
├── use-cases/        🔶 Business logic (AST, chunking, search, workflow)
├── 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.

Self-Orienting Context Layer

When an MCP client connects, the server automatically provides vault context so connected agents can decide when to query this vault and how to use its tools — without explicit user instructions.

Making agents find your vault

The single most important thing: set VAULT_CONTEXT to describe what your vault contains.

{
  "mcpServers": {
    "markdown-vault": {
      "command": "npx",
      "args": ["-y", "@wirux/mcp-markdown-vault"],
      "env": {
        "VAULT_PATH": "/path/to/your/vault",
        "VAULT_CONTEXT": "personal research notes on machine learning and distributed systems"
      }
    }
  }
}

This one-line description is injected into the MCP handshake, the view tool description, and resource headers. When a user asks the agent something related to "machine learning" or "distributed systems", the agent sees the scope match and queries the vault autonomously.

Default: general markdown notes vault (too generic for reliable routing — always set a specific value).

How context is delivered

The server uses four complementary mechanisms so behavior degrades gracefully across clients with different MCP feature support:

Mechanism	When	What the agent sees
	MCP handshake (session start)	Vault scope + tool dispatcher summary. Supported by Claude Desktop, Claude Code, Cursor.
MCP Resources	On-demand via `ReadResource`	`vault://overview` (composed view with live stats + contract + overview), `vault://contract` (raw contract), `vault://stats` (live JSON)
First-call priming	First `view` tool call per session	`_meta.vault_orientation` block with scope + hint to read `vault://overview`
	Tool listing	Includes the `VAULT_CONTEXT` scope string for tool-selection matching

Even if a client supports none of these (rare), the agent still discovers vault content through normal tool use.

Two files: contract vs overview

On first startup, the server creates two files in <VAULT_PATH>/meta/. Both are created once and never overwritten — they are fully yours to edit.

`meta/contract.md` — Tool optimization (power users)

Tells agents how to use the vault's tools efficiently. Pre-filled with sensible defaults:

Section	Purpose	Drives which tool
`## Frontmatter Schema`	YAML keys and types used across notes	`view.frontmatter_get`, `edit.frontmatter_set`
`## Tag Conventions`	Tag naming rules and hierarchies	`view.global_search` query building
`## Search Hints`	Which search action fits which query type	All `view` actions
`## Naming Conventions`	File naming patterns	`vault.create`
`## Note Template`	Default structure for new notes	`vault.create`, `vault.create_from_template`

Most users don't need to edit this. Power users can customize it to match their vault's specific conventions — agents read it via vault://overview and vault://contract resources on each request.

Tip: Add a ## Scope section for a richer, multi-line vault description. Agents see it when reading vault://overview or vault://contract resources.

`meta/overview.md` — Vault narrative (all users)

Free-form description of what the vault currently contains. Created as an empty stub. Write here whatever helps an agent understand your vault's content: active projects, key topic areas, organizational philosophy.

If the body is non-empty, its content is appended to the vault://overview resource that agents can read on demand.

Hot reload behavior

What changed	Effect	Restart needed?
`meta/contract.md`	Reflected in `vault://overview` and `vault://contract` on next read	No
`meta/overview.md`	Reflected in `vault://overview` on next read	No
`VAULT_CONTEXT` env var	Reflected in `instructions` field and `view` tool description	Yes

Migration notes

On first run after upgrade, meta/contract.md and meta/overview.md are auto-created if missing. Existing files are never overwritten. No breaking changes to tool APIs.

If you have a meta/contract.md from other tooling with a different schema, review compatibility — the server-generated contract is dedicated to mcp-markdown-vault navigation hints.

🚢 CI/CD & Release

Fully automated via GitHub Actions and Semantic Release:

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

Versioning follows Conventional Commits — feat: = minor, fix: = patch, feat!: / BREAKING CHANGE: = major
Docker images are built for linux/amd64 and linux/arm64 via QEMU
NPM package published as @wirux/mcp-markdown-vault
Docker image available at ghcr.io/wirux/mcp-markdown-vault

🧪 Testing

516 tests across 46 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.

🔒 Security

🛡️ 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
👤 Docker container runs as non-root user

📄 License

MIT

Install Server

license - permissive license

quality

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

1dRelease cycle

25Releases (12mo)

Commit activity

Resources

Need Help?

Related Servers

Tools

Appeared in Searches

GitHub repository for litopys-dev/litopys project

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wirux/mcp-markdown-vault'

If you have feedback or need assistance with the MCP directory API, please join our Discord server