llm-wiki-mcp
An MCP server for a plain-markdown LLM wiki vault with YAML frontmatter and Obsidian-style wiki-links, enabling headless full-text search, note reading, backlink discovery, and safe append/create-only writing with path traversal protection and an immutable raw/ directory.
README
llm-wiki-mcp
An MCP server for a plain-markdown "LLM wiki" vault — a knowledge base of notes with YAML
frontmatter and Obsidian-style [[wiki-links]], maintained by an LLM librarian. No Obsidian
app or plugin required: the server reads the files directly, so it works headless and
unattended.
Tools
| Tool | Access | What it does |
|---|---|---|
search_wiki(query, limit=20) |
read | Case-insensitive full-text + filename search; filename/title matches rank above body matches. |
read_note(path) |
read | One note: parsed YAML frontmatter, parse error (if any), and markdown body. |
list_recent(n=10) |
read | The n most recently modified notes, newest first (ISO 8601 UTC). |
write_note(path, content, mode, dry_run=False) |
gated write | create a new .md note or append to an existing one. No overwrite mode exists. |
get_links(path) |
read | Outbound [[wiki-links]] and backlinks (matched by filename stem, title, or aliases). |
Safety model
- Path traversal is blocked. Every path resolves inside the vault root or the call fails —
absolute paths,
..segments, and symlink escapes included. - Writes are append/create only. There is no overwrite, no delete, and no rename.
createrefuses existing files;appendrefuses missing ones.dry_run=truepreviews without touching disk. raw/is immutable. The vault's source-material directory rejects all writes.- Only
.mdfiles are writable. - Malformed notes degrade cleanly. Broken YAML frontmatter comes back as a
frontmatter_errorstring with the body intact — never a traceback. - Links in code don't count.
[[links]]inside code fences and inline code are ignored by the link graph (they're examples, not references).
Setup
Requires Python 3.11+ and uv.
git clone <this-repo> llm-wiki-mcp
cd llm-wiki-mcp
uv sync
Point the server at your vault (the directory that contains wiki/):
# PowerShell
$env:LLM_WIKI_VAULT = "C:\path\to\your\vault"
# bash
export LLM_WIKI_VAULT=/path/to/your/vault
Run it standalone (stdio transport):
uv run llm-wiki-mcp
Register with Claude Code
claude mcp add llm-wiki -e LLM_WIKI_VAULT="C:\path\to\your\vault" -- uv run --directory "C:\path\to\llm-wiki-mcp" llm-wiki-mcp
Then in any Claude Code session: "search the wiki for X", "read wiki/concepts/foo.md", "append a journal line to wiki/log.md".
The gardener (scheduled agent)
llm-wiki-gardener is a Claude agent (built on claude-agent-sdk) that tends the vault
through this MCP server. Its entire tool surface is the five tools above — no shell, no
direct file access. Each pass lints recent notes against the vault's conventions, flags
orphans and broken links, proposes crystallization candidates, and files ONE dated report
note at wiki/journal/gardener/YYYY-MM-DD.md via the gated write_note. It never edits
existing notes.
uv run llm-wiki-gardener --vault /path/to/vault # one pass
uv run llm-wiki-gardener --vault /path/to/vault --dry-run # preview, no write
Authentication rides the local Claude Code CLI login. To run weekly on Windows:
schtasks /create /tn llm-wiki-gardener /sc weekly /d SUN /st 21:00 /tr "uv run --directory C:\path\to\llm-wiki-mcp llm-wiki-gardener --vault C:\path\to\vault"
Development
uv run pytest # test suite runs against a synthetic fixture vault (tests/fixtures/vault)
uv run ruff check . # lint
uv run ruff format . # format
The fixture vault is fully synthetic — no real notes, names, or content. Keep it that way.
Design notes
Prior art (what exists, what we adopted, why this was built anyway) is documented in
docs/prior-art.md.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。