keshan's picture
Update README.md
a7c3236 verified

A newer version of the Gradio SDK is available: 6.1.0

Upgrade
metadata
title: Documentation Mcp Tool
emoji: πŸ“š
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.33.1
app_file: app.py
pinned: false
license: mit
tags:
  - mcp-server-track
  - pydocstyle
  - code-analysis
  - documentation
  - modal
short_description: Analyzes Python code for docstring convention

Pydocstyle Documentation Checker (via Modal MCP)

This Gradio application provides an interface to check Python code for documentation style issues using Pydocstyle. The analysis is performed by a Pydocstyle tool running on a Modal Labs Multi-Compute-Platform (MCP) server.

How to Use

  1. Input Parameters:

    • The input field expects a JSON object.
    • This JSON object must contain a key named "code" whose value is the Python code string you want to analyze.
    • An example is pre-filled for convenience:
      {
        "code": "# No module docstring here\n\ndef example_function_missing_docstring():\n    pass\n\nclass ExampleClassMissingDocstring:\n    def method_missing_docstring(self):\n        pass\n\ndef well_documented_function():\n    \"\"\"This function is well documented.\"\"\"\n    return True\n"
      }
      
  2. Submit: Click the "Submit" button.

  3. Output:

    • The application will send the code to the Pydocstyle tool on the Modal MCP server.
    • The results of the Pydocstyle analysis will be displayed as a JSON object in the output field. This JSON will typically include:
      • tool: "pydocstyle"
      • errors: A list of documentation errors found, with details like error code, message, and line number.
      • files_checked: Number of files checked (usually 1 for the provided code snippet).
      • Any errors encountered during the process.

Configuration

For this application to function correctly, the MODAL_MCP_ENDPOINT environment variable must be set. This variable should point to your deployed Modal function that handles MCP tool execution (e.g., the /execute_tool endpoint).

  • Create a .env file in the mcp_deploy directory (or the root of your Space if deploying to Hugging Face Spaces and it's not automatically picked up from this directory).
  • Add the following line to the .env file, replacing the placeholder with your actual Modal endpoint URL:
    MODAL_MCP_ENDPOINT="https://your-username--mcp-server-app-execute-tool.modal.run"
    

If the MODAL_MCP_ENDPOINT is not set or is incorrect, the application will display an error message upon submission.

Next step

Add more tools to analyse different other aspects.