Kybase
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kybasesearch my notes about meeting notes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kybase is a complete, self-contained Markdown notes application and MCP (Model Context Protocol) server.
For You: A sleek web-based notes editor with wikilinks
[[Title]], an interactive visual knowledge graph, backlinks, and bilingual hybrid search.For Claude (Claude Code / Desktop): A persistent memory vault that survives across chats, automatically growing and linking notes as you work.
Everything runs locally on your machine via Docker: PostgreSQL for notes, pgvector + Ollama for embeddings. No SaaS, no accounts, 100% private.
Why Kybase?
Giving an agent persistent memory usually means assembling it yourself:
a notes app, an MCP bridge, an embedding pipeline, and sync between them.
Kybase is that whole stack as one docker compose up:
MCP-native — 13 tools (
search_notes,get_note_with_links,get_graph,get_backlinks, CRUD for notes/folders) over Streamable HTTP, with instructions that teach the agent to interlink notes properlyLocal semantic search — pgvector + Ollama embeddings, private by default; hybrid RRF fusion with bilingual full-text search
Agent-friendly graph — explicit wikilink edges plus semantic edges computed from embedding similarity, so the agent discovers related notes that were never linked
Zero external services — app, Postgres+pgvector, and Ollama in one compose file; single-secret auth
Related MCP server: trip2g
Features
Markdown notes with wikilinks —
[[Title]]links between notes, backlinks panel; renaming a note rewrites its wikilinks everywhereGraph view — link edges plus semantic edges with a similarity slider
Hybrid search — RRF fusion of pgvector cosine similarity and bilingual FTS, chunked embeddings, excerpt-based results
Workspace focus mode — filter tree, graph, and search down to one top-level folder
Pluggable embeddings — Ollama (local, default), Google, or OpenAI, all 768-dim, switchable without schema changes
Stack
Layer | Tech |
Frontend | Next.js App Router, React 19 |
Database | PostgreSQL 16 + pgvector (direct |
Embeddings | Ollama |
Search | RRF hybrid: pgvector HNSW cosine + bilingual FTS |
MCP |
|
Auth | Single |
Quick Start (Docker)
git clone https://github.com/Kyrzin/kybase.git
cd kybase
cp .env.example .env
# edit .env: set KYBASE_SECRET (openssl rand -hex 32)
docker compose up -d --buildOpen http://localhost:3000 and log in with your KYBASE_SECRET.
That's it. On first start Postgres applies db/migrations/*.sql
automatically and Ollama downloads the embedding model (~270 MB, one time).
Change the host port with KYBASE_PORT in .env.
Note on embeddings: notes and text search work immediately. Semantic search and semantic graph edges activate once Ollama finishes pulling the model and notes get indexed (automatic, in the background).
Connect Claude (MCP)
The app exposes a Streamable HTTP MCP endpoint at /api/mcp.
Claude Code — add to .mcp.json (or claude mcp add):
{
"mcpServers": {
"kybase": {
"type": "http",
"url": "https://your-domain/api/mcp",
"headers": {
"Authorization": "Bearer <KYBASE_SECRET>"
}
}
}
}claude.ai — Settings → Connectors → Add custom connector, same URL (requires the instance to be reachable over HTTPS).
Available tools: list_notes, get_note, get_note_with_links,
create_note, update_note, delete_note, search_notes, list_folders,
create_folder, update_folder, delete_folder, get_backlinks, get_graph.
The server ships with MCP instructions that teach the agent to search before
writing and to add [[wikilinks]] to related notes — so the knowledge graph
grows as the agent uses it, instead of accumulating orphan notes.
Local development
# Postgres only (app runs on the host)
docker compose up -d db
cp .env.example .env.local
# in .env.local: set KYBASE_SECRET and uncomment DATABASE_URL
npm install
npm run dev # http://localhost:3000Switching Embedding Providers
You can switch the embedding provider (between local Ollama, Google, or OpenAI) and trigger re-indexing directly in the browser:
Open the settings modal in the web UI.
Select your provider, add the API key if needed, and click Save & Apply (switching the provider automatically triggers background re-indexing).
Alternatively, click Reindex to force-reindex all your notes.
All supported providers use 768-dimensional embeddings, so switching does not require any database schema changes.
CLI Alternative: If you prefer using the terminal, you can trigger re-indexing by calling the admin endpoint:
docker compose exec kybase node -e " fetch('http://localhost:3000/api/admin/reindex', { method: 'POST', headers: { Authorization: 'Bearer <KYBASE_SECRET>' } }).then(r => r.json()).then(console.log) "
Upgrading
docker-entrypoint-initdb.d migrations only run on a fresh database volume.
When an upgrade ships a new db/migrations/NNN_*.sql, apply it manually:
docker compose exec -T db psql -U kybase kybase < db/migrations/NNN_name.sqlDevelopment
npm test # Vitest unit tests (wikilinks, embeddings, search/RRF)
npm run build # Production build check
npx tsc --noEmit # Type checkLicense
PolyForm Noncommercial 1.0.0 — free to use, modify, and share for any noncommercial purpose. Commercial use requires a separate license from the author.
Required Notice: Copyright © Denis Kurzin (https://github.com/Kyrzin)
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Kyrzin/kybase'
If you have feedback or need assistance with the MCP directory API, please join our Discord server