wiznote-mcp

wiznote-mcp

Enables Claude to interact with a private WizNote server for document management, including creating, reading, searching, and updating notes.

Category
Visit Server

README

wiznote

Use WizNote as your doc source of truth in Claude-driven development.

English | 简体中文

wiznote is a public, privacy-safe Claude skill and Python helper set for developers who want a lightweight documentation workflow: private WizNote deployment, repo-local mirrors, and Claude-friendly operations in one package.

It is built for personal developers and small teams doing vibe coding, where plans, notes, specs, and implementation context need to stay close to the code without introducing a heavy documentation platform.

Why developers may want this

  • Private by default — connect to your own WizNote deployment instead of moving docs into a public SaaS workspace
  • Claude-friendly workflow — pair the same doc system with Claude Code and adjacent desktop, web, or IDE-centered repo workflows
  • Cross-end continuity — write or sync on one surface, continue from another, and keep the same documentation source of truth
  • Built for personal or small-team vibe coding — keep docs, plans, and implementation notes tightly coupled to the codebase
  • Repo mirrors included — keep WizNote as canonical while preserving code-adjacent Markdown copies in docs/wiznote-mirror/...

This package is derived from a private internal workflow, but all user-specific paths, hosts, credentials, and organization-specific folder mappings have been removed.

Latest Updates

2026-07-04

  • Added a local stdio MCP adapter for existing WizServer deployments.
  • Added tools for folder creation, note search/read, and note create/update workflows.
  • Added the wiznote-mcp package entrypoint and generic MCP configuration docs.

Full history: docs/releases/release-notes.md

What it includes

  • SKILL.md — the Claude Code skill definition
  • wiznote_cli.py — login, list, download, create, and update note helpers
  • wiznote_helper.py — category validation, mirror-path generation, and HTML body extraction helpers
  • wiznote_mcp.py — local stdio MCP adapter that calls an existing WizServer HTTP API
  • tests/ — pytest coverage for the publicized helper and CLI behavior

Features

  • Log in to a WizNote server with explicit credentials or environment variables
  • Use WizNote through a local MCP server without running another Docker container
  • List notes under a configurable category root
  • Create WizNote folders/categories
  • Search notes
  • Download note HTML
  • Create new notes from generated HTML
  • Update existing notes
  • Mirror notes into docs/wiznote-mirror/... safely
  • Validate category paths so sync stays inside your chosen root
  • Support Unicode note titles for mirror filenames

Requirements

  • Python 3.11+ recommended
  • A reachable WizNote server
  • Optional Python packages depending on your workflow:
    • markdown for Markdown → HTML conversion
    • pytest for running the included tests

Installation

Option 1: Use as a Claude Code skill

Copy this directory to your Claude skills directory:

mkdir -p ~/.claude/skills
cp -R ./wiznote ~/.claude/skills/wiznote

Option 2: Keep it in your repository

You can also keep wiznote/ inside your repo and import the Python files directly in your own scripts.

Configuration

Set these environment variables:

export WIZNOTE_BASE_URL="https://notes.example.com"
export WIZNOTE_USER="you@example.com"
export WIZNOTE_PASSWORD="your-password"

You also need two runtime values in your scripts:

  • category_root — the top-level WizNote category you want to sync under, for example /team/docs/
  • repo_root — the local repository root used for mirror output

Local MCP adapter

wiznote_mcp.py is a stdio MCP server. It does not require a separate Docker container and does not modify your existing WizServer deployment. The MCP process connects directly to the existing WizServer HTTP API.

Example MCP configuration:

{
  "mcpServers": {
    "wiznote": {
      "command": "python3",
      "args": [
        "/path/to/wiznote/wiznote_mcp.py",
        "--base-url",
        "http://127.0.0.1:18080",
        "--username",
        "you@example.com",
        "--password",
        "your-password"
      ]
    }
  }
}

If your MCP client keeps secrets in environment variables, omit the arguments and set WIZNOTE_BASE_URL, WIZNOTE_USER, and WIZNOTE_PASSWORD instead.

Available MCP tools:

  • wiz_create_folder — create a WizNote category/folder
  • wiz_list_notes — list notes in a category/folder
  • wiz_search_notes — search notes
  • wiz_get_note — read note metadata and HTML body
  • wiz_create_note — create a note from HTML or basic Markdown
  • wiz_update_note — update an existing note from HTML or basic Markdown

The MCP adapter writes through WizServer APIs only. It does not write directly to MySQL or /wiz/storage, so WizServer still owns permissions, versions, object data, and indexing.

Quick start

1. Import the helpers

from pathlib import Path
import sys

SKILL_DIR = Path("/path/to/wiznote")
sys.path.insert(0, str(SKILL_DIR))

import wiznote_cli as cli
import wiznote_helper as helper

2. Load credentials and log in

creds = cli.load_credentials()
login = cli.login(creds)

Or pass credentials explicitly:

creds = cli.load_credentials(
    base_url="https://notes.example.com",
    user="you@example.com",
    password="your-password",
)
login = cli.login(creds)

3. Choose a category root and target category

category_root = helper.normalize_category_root("/team/docs/")
category = helper.resolve_category(category_root, "plans/")

4. List notes

payload = cli.fetch_note_list(
    base_url=login.kb_server,
    kb_guid=login.kb_guid,
    token=login.token,
    category=category,
)

5. Create a note

html = "<h1>Project Design</h1><p>...</p>"

result = cli.create_note(
    base_url=login.kb_server,
    kb_guid=login.kb_guid,
    token=login.token,
    title="Project Design",
    category=category,
    html=html,
)

6. Build a safe local mirror path

mirror_path = helper.mirror_output_path(
    repo_root=Path("/path/to/repo"),
    category_root=category_root,
    category=category,
    title="Project Design",
)

Recommended sync flow

  1. Configure credentials
  2. Normalize the category root
  3. Log in once and reuse the session
  4. Resolve the exact target category
  5. List notes before writing
  6. Convert Markdown to HTML
  7. Create or update the note in WizNote first
  8. Refresh the local mirror second
  9. Re-list the category to verify the write

Markdown to HTML

create_note(...) and save_note(...) expect HTML, not raw Markdown.

Example:

python3 -m pip install markdown
import markdown

html = markdown.markdown(text, extensions=["extra", "fenced_code", "tables", "sane_lists"])

Running tests

python3 -m pip install pytest
pytest wiznote/tests

Privacy and publishing notes

This public version intentionally avoids:

  • hardcoded home directories
  • private server addresses
  • usernames or passwords
  • organization-specific project folder mappings

If you fork or modify it, keep your published copy free of private infrastructure details.

File layout

wiznote/
├── README.md
├── README.zh-CN.md
├── SKILL.md
├── wiznote_cli.py
├── wiznote_helper.py
├── wiznote_mcp.py
└── tests/
    ├── conftest.py
    ├── test_cli.py
    └── test_helper.py

License

MIT. See LICENSE.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured