KnowledgeBase

A Model Context Protocol server for extracting text from documents and creating Excel workbooks with formatting.

python

1

GitHub Stars

python

Language

4 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": {
    "mehmetozcan-zz-knowledgebasemcp": {
      "command": "python",
      "args": [
        "path/to/KnowledgeBaseMCP/launch_mcp.py"
      ]
    }
  }
}

You run KnowledgeBaseMCP to read text from common document formats such as PDF, DOCX, PPTX, and XLSX, and to create structured Excel workbooks from data. This MCP server lets you extract content from your local documents, analyze it with AI assistants, and generate organized reports and spreadsheets with formatting and multiple sheets.

How to use

You connect your MCP client to the KnowledgeBaseMCP server so you can request document reading and Excel creation capabilities. Use the available tools to extract text from a single file, from an entire directory, or to create new Word or Excel documents from data. You can process directories recursively if you want to include subfolders, and you can generate formatted reports or append data to existing spreadsheets.

How to install

# Prerequisites
Python 3.8 or higher
Claude Desktop application

# Step 1: Clone the project
git clone https://github.com/mehmetozcan-zz/KnowledgeBaseMCP.git
cd KnowledgeBaseMCP

# Step 2: Install dependencies
pip install -r requirements.txt

# Step 3: Test the server
python test.py

Configuration and using with Claude Desktop

Integrate the MCP server with Claude Desktop by adding a new MCP server entry in your Claude Desktop configuration. The following example shows how to run the MCP server locally as a stdio process using Python and the launcher script.

{
  "mcpServers": {
    "knowledgebase": {
      "command": "python",
      "args": ["path/to/KnowledgeBaseMCP/launch_mcp.py"]
    }
  }
}

Available tools

extract_text_from_file

Extract text content from a single document file.

extract_text_from_directory

Extract text content from all supported documents in a directory.

list_supported_files

List all supported document files in a directory with metadata.

create_docx_document

Create a new Word document with text content.

create_structured_report

Create a structured Word report with formatting.

create_xlsx_workbook

Create a new Excel workbook with multiple sheets.

create_xlsx_from_dataframe

Create Excel workbook from pandas DataFrames.

append_to_xlsx

Append data to an existing Excel workbook.

create_xlsx_report

Create a formatted Excel report with multiple sections.