wissensdatenbank-mcp
Pulls and incrementally syncs a Markdown/Obsidian vault from a Git repository on a schedule, including private repositories over SSH.
Supports syncing a private vault from a Gitea-hosted Git repository via SSH.
Supports syncing a private vault from a GitHub-hosted Git repository via SSH.
Supports syncing a private vault from a GitLab-hosted Git repository via SSH.
Indexes Markdown notes as the knowledge base content and provides hybrid section search with snippets, links, and backlinks.
Indexes and searches an Obsidian vault, honoring frontmatter, tags, wikilinks with aliases/headings, links/backlinks, and related-note traversal.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
wissensdatenbank-mcp
Hybrid search over a Markdown/Obsidian vault as an MCP server – self-hosted, incremental, with per-account access control.
Wissensdatenbank is German for knowledge base. The server pulls a vault from a Git repository (or reads a mounted folder), indexes it and lets AI assistants such as Claude, Hermes, Open WebUI or any other MCP client search it. Each client gets its own token, and each token only sees the notes its account is allowed to see.
Git repository ──pull every 5 min──▶ ┌────────────────────────────┐ ◀── MCP (Streamable HTTP) ── AI assistants
(Obsidian vault) │ wissensdatenbank-mcp │ Bearer token per account
│ LanceDB · bge-m3 · reranker│
access.yaml (file or Git repo) ────▶ │ access filter on every tool│ ◀── wdb CLI (inside the container)
└────────────────────────────┘Features
Hybrid search: multilingual embeddings (BAAI/bge-m3) + full-text search with stemming and stop words, fused with reciprocal rank fusion, plus notes linked from the best hits (wikilinks), re-scored by a cross-encoder.
Obsidian-aware: frontmatter, tags (also inline
#tags, hierarchicala/b),[[wikilinks]]with aliases and headings; results includelinksandbacklinks;related_noteswalks the link graph.Access control: accounts with allow/deny rules on tags, folders, path patterns and frontmatter fields, reusable roles, several tokens per account. Rules are applied as a database prefilter in every search path and to every tool – hidden notes behave as if they did not exist. Policy changes apply immediately, without re-indexing. See docs/access-control.md.
Always available: updates build a new table version in the background; searches keep running on the previous state until the switch-over. Failed or cancelled updates roll back.
Incremental: only new, changed and deleted notes are processed. Embeddings are cached by text hash and checkpointed every 60 seconds, so a crash or restart never loses computed work.
Operations: one status line per minute while long tasks run (silent when idle),
/healthendpoint, administration CLIwdb(status, stats, rebuild, cancel, pause, cache, test search, quality evaluation, account management).Scales: tested with 5,600 notes / 80,500 sections – rebuild from cache in 10 s, incremental update < 1 s, search 0.1–0.4 s on CPU. A vector index is created automatically above 50,000 sections.
Related MCP server: qkb
Quick start
Try it with the bundled example vault (no Git needed):
git clone https://github.com/bierwirth-it/wissensdatenbank-mcp.git
cd wissensdatenbank-mcp
docker compose -f docker-compose.build.yml -f docker-compose.local.yml up --buildThe first start downloads the models (~3 GB, cached in a volume) and builds the index. When the log shows New index state active, test it:
docker compose -f docker-compose.build.yml -f docker-compose.local.yml exec wissensdatenbank-mcp wdb search "How do I request vacation?"The MCP endpoint is http://localhost:8765/mcp. Without a token or access policy the server is open – fine for a local test, not for anything else.
Deployment
Option | Guide |
Docker / Docker Compose with the prebuilt image ( | |
Coolify, building from this repository | |
Coolify, using the prebuilt image |
Minimal .env for a private vault on GitHub/GitLab/Gitea:
GIT_REPO_URL=ssh://git@github.com/acme/knowledge-base.git
GIT_SSH_PRIVATE_KEY="-----BEGIN OPENSSH PRIVATE KEY-----
...
-----END OPENSSH PRIVATE KEY-----"
GIT_SSH_KNOWN_HOSTS="github.com ssh-ed25519 AAAA..."
FTS_LANGUAGE=English # language of the vault for full-text stemmingThen create the first account inside the container:
docker compose exec wissensdatenbank-mcp wdb account add admin --all --adminMCP tools
Tool | Purpose |
| Best section per note: |
| Full note with links and backlinks |
| Linked notes, backlinks and (depth 2) notes two steps away |
| Notes visible to the account |
| Index state; full details with the |
| Pull the repository now ( |
Client configuration (Claude Desktop, Claude Code, Hermes, Open WebUI, generic): docs/clients.md.
Documentation
Deployment – Docker, Docker Compose, Coolify (repository or image), Git access, reverse proxy, updates
Access control – accounts, roles, rules, tokens, policy in Git, how filtering works
Configuration – all environment variables
Search – how search works, tuning and measuring quality
Clients – connecting MCP clients
Development – tests, CI, releases
Requirements
x86-64 or ARM64 host, 4 GB RAM (2 GB used at idle with the default models), ~6 GB disk for image and models.
CPU only; no GPU needed. More cores speed up the first indexing (roughly 2–5 minutes per 1,000 notes on 8 cores).
Licence
MIT © André Bierwirth (Bierwirth-IT). Third-party components and models: THIRD_PARTY_NOTICES.md – note the licence remark on the default reranker model.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Search your knowledge bases from any AI assistant using hybrid RAG.
Personal context for every AI: search, read, and write back to your private Markdown library.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI-powered chat and file operations on Obsidian vaults with local indexing, hybrid search, and MCP access.-
- AlicenseNot gradedqualityBmaintenanceProvides a hybrid search engine for Obsidian vaults, enabling LLM agents to query notes with BM25 keyword and vector semantic search, metadata filtering, and sibling-document retrieval.70 npmMIT
- FlicenseAqualityDmaintenanceProvides AI assistants with tools to manage Obsidian notes via hybrid semantic search (BM25, Voyage AI, Cohere), full CRUD, backlinks, and live indexing without restart.121-
- AlicenseNot gradedqualityCmaintenanceEnables hybrid vector-BM25 search and retrieval of Obsidian vault knowledge notes, allowing AI assistants like Claude to efficiently access relevant chunks without full file reads.MIT