- Home
- MCP servers
- Document360
Document360
- python
3
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"druellan-document360-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/document360-mcp/folder",
"run",
"server.py"
],
"env": {
"DOCUMENT360_API_KEY": "your_api_key_here",
"DOCUMENT360_BASE_URL": "https://apihub.document360.io"
}
}
}
}You can access and read Document360 knowledge base content through a minimal MCP server. This server exposes a few read-only endpoints to retrieve categories, pages, articles, and project versions, enabling lightweight integration with knowledge bases in your MCP client.
How to use
You connect an MCP client to the Document360 MCP server and perform read operations to discover project structure and fetch content. The server exposes actions to fetch categories, get individual category pages, retrieve articles, and browse project versions. Use these tools to build features like searchable knowledge bases, article readers, and navigable category trees within your client.
How to install
Prerequisites you need on your host before running the server:
- Python 3.8 or newer
- A valid Document360 API key
Install and run steps
# Optional: create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate.bat`
# Install dependencies
pip install -r requirements.txt
# Start the MCP server using UV (recommended)
uv run server.py
Additional configuration and startup notes
You can configure the server by setting environment variables for your API key and base URL. The default base URL is https://apihub.document360.io, but some accounts require a regional base URL such as https://apihub.us.document360.io. Provide these values in the runtime environment to initialize the MCP server correctly.
Additional sections
Usage, configuration, and troubleshooting details mirror the access patterns described below. The MCP server is designed to be minimal and focus on discover/read operations: get category by ID, get category page content by ID, get article by ID, search in project versions, and list project versions. Ensure your API key is kept secure and not exposed in client code.
Available tools
get_category
Retrieve a Document360 category by its UUID to explore category metadata and related pages.
get_category_page_content
Fetch the content of a specific category page by its category_id and page_id to render the page inside your MCP client.
get_article
Retrieve an article by its UUID to display full article text and metadata.
search_in_project
Search within a specific project version to find relevant content across documents.
list_project_versions
List all available project versions for navigation and filtering in your client.