Skip to main content
Glama

Document360 MCP Server

Model Context Protocol server for Document360 that enables AI assistants to search, retrieve, and interact with your knowledge base. Built with FastMCP, this server provides seamless access to Document360 articles, categories, and project versions through a standardized MCP interface.

Features

  • Get Category by ID

  • Get Category Page Content by ID

  • Get Article by ID

  • Search in Project Versions

  • List Project Versions

Related MCP server: Amplemarket Knowledge Base MCP Server

Requirements

  • Python 3.12+

  • Document360 API key

Installation

Clone or download this repository, then install dependencies:

pip install -r requirements.txt

or using a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate.bat`
pip install -r requirements.txt

or using UV

uv venv
uv pip install -r requirements.txt

Configuration

Set your Document360 API key and other environment variables. You can do this in your shell or directly in the mcp-config.json file:

{
  "mcpServers": {
    "document360": {
      "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"
      }
    }
  }
}

Note: the default base URL is https://apihub.document360.io, but some accounts require to use the regional base url https://apihub.us.document360.io.

Usage

Run the server directly:

python server.py

Or with UV:

uv run server.py

Exposed MCP Tools

Although Document360 exposes more granular endpoints, these are sufficient for a simple consumption workflow: models can discover project versions, enumerate categories and pages, and retrieve full page contents.

  • get_category_page_content Parameters:

    • category_id (UUID string): Document360 category ID

    • page_id (UUID string): Document360 page ID

  • get_article Parameters:

    • article_id (UUID string): Document360 article ID

  • search_in_project Parameters:

    • project_version_id (UUID string): Document360 project version ID

    • query (string, optional): Free-text phrase searched across articles/categories by the Document360 backend

    • hits_per_page (int, optional, default 20): Maximum number of ranked results to return (1-1000)

  • list_project_versions Parameters: none

  • get_category Parameters:

    • category_id (UUID string): Document360 category ID

License

MIT

Available Tools

5 tools
get_articleA
Read-only

Get article by ID from Document360

Inputs: article_id (required). Returns: object

get_categoryB
Read-only

Get category by ID from Document360

Inputs: category_id (required). Returns: object

get_category_page_contentB
Read-only

Get category page content by ID from Document360

Inputs: page_id (required), category_id (required). Returns: object

list_project_versionsA
Read-only

List all project versions from Document360

Inputs: no named parameters. Returns: object

search_in_projectA
Read-only

Search inside a project version and return related articles/categories in Document360

Inputs: project_version_id (required), query, hits_per_page. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation4/5

    Most tools target clearly distinct resources and actions. The only likely confusion is between get_category and get_category_page_content, since both retrieve category data by ID and the descriptions do not make the distinction explicit.

    Naming Consistency5/5

    Tool names consistently follow a clear verb_noun snake_case pattern: get_*, search_in_project, and list_project_versions. The naming style is uniform and predictable, making it easy for an agent to infer the purpose of each tool.

    Tool Count5/5

    Five tools is a well-scoped size for a read-oriented knowledge base server. Each tool covers a meaningful retrieval or search operation without unnecessary redundancy or bloat.

    Completeness4/5

    The set covers the core read/search workflows for articles, categories, category page content, and project versions. It lacks list-all endpoints and any mutation capabilities, but for a retrieval-focused Document360 assistant the coverage is workable.

    Maintenance

    ActivityStale
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers