kmd
MCP server for structured markdown knowledge vaults that provides validation, FTS5 search, and wikilink cross-references. Enables AI agents to prime context and search across vaults using two MCP tools and template resources.
README
kmd — knowledge-markdown
CLI + MCP server for structured markdown knowledge vaults. Validate, index (SQLite FTS5), and serve content to AI agents — one npx away.
Same primitives as Open Knowledge Format (markdown + YAML frontmatter + directory tree), but opinionated where OKF is minimal:
| OKF | kmd | |
|---|---|---|
| Vocabulary | open — producer picks type values |
controlled — vault.yaml defines kinds, scopes, statuses, tags; kmd validate enforces |
| Structure | flat — organize however | three domains: projects/ · research/ · notes/ |
| Validation | none — format spec only | deterministic, LLM-free; gates sync + pre-commit hook |
| Cross-refs | bundle-relative /path.md |
[[wikilinks]] (Obsidian-native, rename-safe, no-dangling guarantee) |
| Agent surface | none — bring your own | two MCP tools (prime, search) + template resources |
| Infrastructure | n/a | node:sqlite FTS5; zero external deps |
Install
npx @bartolli/kmd --help
Commands
kmd validate [<path>] deterministic vault checker (default: $WIKI_VAULT)
kmd sync vault → SQLite index (runs validate first)
kmd mcp [<vault-root>] stdio MCP server
kmd db reset delete and recreate the index
MCP registration
{
"mcpServers": {
"wiki": {
"command": "npx",
"args": ["-y", "@bartolli/kmd", "mcp", "/absolute/path/to/vault"]
}
}
}
Two tools:
prime(scope, task?)— orientation briefing: identity, primer, active ADRs, plan, vocabulary, hubs, task-relevant pages.search(query, scope?, kind?, limit?)— FTS5 ranked candidates{path, title, kind, summary, score}. Never page bodies.
Templates served as MCP resources at wiki://template/{domain}/{kind}.
Vault structure
vault/
├── vault.yaml # controlled vocabulary
├── templates/ # frontmatter templates → MCP resources
├── projects/{scope}/ # specs, ADRs, plans, stories
├── research/{topic}/ # articles, sources
└── notes/ # low-ceremony capture
Development
Requires Node.js 22+ (node:sqlite FTS5) and pnpm 11+.
pnpm install
pnpm -r run typecheck && pnpm -r run test && pnpm lint
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.