MCP server that turns raw sources into an interlinked Obsidian wiki with Claude Code.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"wiki-agent": {
"env": {
"RAW_PATH": "/absolute/path/to/raw",
"WIKI_PATH": "/absolute/path/to/wiki",
"OPENAI_API_KEY": "sk-..."
},
"args": [
"-jar",
"/absolute/path/to/wiki-agent.jar"
],
"type": "stdio",
"command": "java"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A personal knowledge management system that turns raw sources — URLs, PDFs, audio, video — into an interlinked wiki. Built as an MCP server in Kotlin + Spring Boot, it pairs with Claude Code: the server is the toolkit, Claude is the brain.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in productivity / writing
Persistent memory using a knowledge graph
Dynamic problem-solving through sequential thought chains
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
MCP Security Weekly
Get CVE alerts and security updates for Llm_wiki_agent and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A personal knowledge management system that turns raw sources — URLs, PDFs, audio, video — into an interlinked wiki. Built as an MCP server in Kotlin + Spring Boot, it pairs with Claude Code: the server is the toolkit, Claude is the brain.
Inspired by Andrej Karpathy's pattern of using LLMs to incrementally build a personal wiki instead of RAG.
Claude Code (LLM — all intelligence)
│ MCP protocol (STDIO)
▼
Wiki Agent Server (toolkit — zero LLM calls)
├── Content extraction (URL, PDF, text, audio, video)
├── Wiki management (CRUD, search, index, log)
│
▼ filesystem
wiki/ (Obsidian vault) raw/ (immutable sources)
You give Claude Code a URL, PDF, or audio file. It calls the server to extract content, then uses its own intelligence to distill it into wiki pages with proper structure, cross-links, and metadata. The wiki is an Obsidian-compatible vault you can browse and search.
brew install ffmpeg)git clone <repo-url> && cd llm_wiki_agent
./gradlew bootJar
This produces build/libs/wiki-agent.jar (~70MB, includes Apache Tika).
claude mcp add -s user wiki-agent \
-- java -jar /absolute/path/to/llm_wiki_agent/build/libs/wiki-agent.jar
Use -s user to make the server available in all projects. Use -s project for the current project only.
By default, the wiki and raw directories are created relative to the working directory. For a persistent setup, set absolute paths in ~/.claude.json under the mcpServers entry:
{
"mcpServers": {
"wiki-agent": {
"type": "stdio",
"command": "java",
"args": ["-jar", "/absolute/path/to/wiki-agent.jar"],
"env": {
"WIKI_PATH": "/absolute/path/to/wiki",
"RAW_PATH": "/absolute/path/to/raw",
"OPENAI_API_KEY": "sk-..."
}
}
}
}
claude mcp list
# wiki-agent: java -jar ... - ✓ Connected
Open your wiki/ directory as an Obsidian vault to get a graph view of all your pages and their [[wikilinks]].
| Tool | Description |
|---|---|
wiki_extract | Extract content from a URL, PDF, or text file. Auto-detects source type. Saves raw extraction to raw/. |
wiki_transcribe | Transcribe audio/video via OpenAI Whisper. For video, extracts audio with ffmpeg first. Requires OPENAI_API_KEY. |
| Tool | Description |
|---|---|
wiki_write_page | Create or overwrite a wiki page. Content should include YAML frontmatter. |
wiki_read_page | Read a wiki page by filename. |
wiki_delete_page | Delete a page. index.md and log.md are protected. |
wiki_list_pages | List all pages with titles and file sizes. |
wiki_update_index | Overwrite index.md (master table of contents). |
wiki_append_log | Append a timestamped entry to log.md. |
wiki_search | Case-insensitive keyword search across all pages. Returns matching lines with context. |
wiki_status | Page count, raw source count, last log entry, total wiki size. |
Once the server is connected, talk to Claude Code naturally:
Ingest a URL:
"Read this article and add it to the wiki: https://example.com/interesting-article"
Ingest a PDF:
"Extract this paper and create wiki pages from it: /path/to/paper.pdf"
Transcribe a lecture:
"Transcribe this lecture a