markdown-vault-mcp
Active·★ 35·MIT·Updated 2026-10-21
This tool is a generic Model Context Protocol (MCP) server designed for managing markdown collections, featuring full-text and semantic search capabilities. It allows users to point it at a directory of markdown files and exposes search, read, write, and edit tools over the MCP, supporting various vault types like Obsidian or Zettelkasten.
#Markdown Vault#Knowledge Base#Full-Text Search (FTS5)#Semantic Search#Vector Search#Model Context Protocol (MCP)#AI Tooling#Git Integration
01
Features
01Full-text and Semantic Search: Combines SQLite FTS5 with BM25 scoring and semantic vector search using embeddings (FastEmbed, Ollama, OpenAI), including hybrid search with Reciprocal Rank Fusion.
02Adaptive Heading-Level Chunking: Recursively splits long sections at deeper heading levels until each chunk fits a configurable word budget, enhancing retrieval precision for LLMs.
03Comprehensive Vault Management: Provides frontmatter-aware indexing, incremental reindexing, write operations (create, edit, delete, rename), and support for non-markdown attachments.
04LLM-Visible Tools and Resources: Offers over 30 LLM-visible tools for vault interaction (search, read, write, admin) and 9 resources for accessing vault metadata (config, stats, tags).
05Git Integration and OIDC Authentication: Features optional auto-commit and push on writes via Git integration, alongside robust OIDC authentication for secure HTTP deployments.
02
Compatibility
Python
Runtime
Verified via docs
Docker
Container
Verified via docs
Claude Desktop
Integration
Verified via docs
Claude Code Plugin
Integration
Verified via docs
03
Quick start
1
$ pip install markdown-vault-mcp
04
Use cases
↳Capture a URL as a Note: Automatically fetch, summarize, and save web content as a structured note within the vault, linking to related existing notes.
↳Research Topics into Your Vault: Conduct in-depth research on a topic, compare findings, and generate a set of interlinked notes within the vault, including a map-of-content.
↳Distill Daily Conversations: Summarize and capture key insights from daily conversations directly into designated 'Inbox' notes for later organization.
↳Split or Merge Notes: Efficiently restructure notes by splitting a single note into multiple new ones or merging content into an existing note, avoiding duplication.
05
Alternatives
mcp-logseq★ 343
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
Hatchdoor★ 61
Self-hosted, agent-native web app and MCP server for your Obsidian-style Markdown vault. Browse, search, and edit notes from a fast UI or from AI agents.
openchronicle-mcp★ 16
Memory database for LLM agents — persistent keyword + optional semantic memory, project namespacing, served over HTTP REST and MCP from a single ASGI process. SQLite-backed, packaged as a Docker container. Runs on your hardware.
tela★ 84
Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.
zoteus★ 61
⚡ The everything Zotero MCP server: complete Zotero Web API v3 + desktop local API for Claude & any MCP client. Search, safe writes, add-by-DOI, CSL citations, hybrid semantic search, and a scholarly-context graph. TypeScript, local-first.
Comments
Log in to leave a comment
No comments yet. Be the first!