obsidian-wiki-mcp
MCP server that implements Karpathy's LLM Wiki pattern for Obsidian vaults, enabling persistent knowledge storage and BM25 search across AI sessions.
README
Obsidian wiki MCP
MCP server implementing Karpathy's LLM Wiki pattern for Obsidian vaults.
Solves document drift — your vault stays up-to-date as knowledge evolves across AI sessions.
fluid not opinionated — bring your own folder structure
storage not intelligence — the server stores; the LLM decides
always searchable — BM25 index rebuilt on every write
Design principle: The server is a pure storage/retrieval layer. All content decisions (what to write, how to synthesize) are made by the host LLM (Claude). The server never calls an AI model.
Quick Start
1. Add to your AI client:
Claude Code
claude mcp add obsidian-wiki -- npx -y obsidian-wiki-mcp --vault "/path/to/your/vault"
Kiro CLI
kiro mcp add obsidian-wiki -- npx -y obsidian-wiki-mcp --vault "/path/to/your/vault"
OpenAI Codex CLI
codex --mcp-config '{"obsidian-wiki":{"command":"npx","args":["-y","obsidian-wiki-mcp","--vault","/path/to/your/vault"]}}'
Paths with spaces must be quoted. See Configuration for all installation options.
2. Initialize the vault:
Call wiki_init() to initialize the vault.
3. Start using:
Ingest this session into the wiki: [paste content]
Use wiki_query to find information about [topic]
Documentation
| Doc | Description |
|---|---|
| Getting Started | First-time setup, existing vault migration, CLAUDE.md / AGENTS.md |
| Vault Structure | Folder layout, page format, tags, naming convention |
| Tools Reference | All MCP tools with parameters and examples |
| Workflows | Common usage patterns |
| Configuration | Claude Code setup, server config file |
| Troubleshooting | Common issues and fixes |
Recent tool contract update:
wiki_write_pageandwiki_apply_fixnow include adifffield (unified diff) in write responses where applicable.- See Tools Reference for exact behavior by tool/action.
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.