AutoDoc Server

AutoDoc is an MCP server of type stdio that automatically analyzes Git commits and generates structured daily CSV reports.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio iseduardorezende-autodoc-mcpserver dotnet run --project C:/path/to/AutoDocMcpServer/AutoDocMcpServer.csproj \
  --env RULES="Analyze only relevant commits. Ignore merges and noisy commits. Use phases: Development, Tests, Infrastructure, Integration. Summarize titles using the configured culture. Use OWNER_NAME for Participants. Be brief and objective." \
  --env CULTURE="en-US" \
  --env OWNER_NAME="Project Owner" \
  --env OUTPUT_PATH="C:\Reports" \
  --env OWNER_EMAIL="owner@example.com" \
  --env REPOSITORY_PATH="C:\path\to\repo" \
  --env PROJECT_METADATA="Short project summary to include in report context." \
  --env REPORT_COLUMNS_TITLES="Period,Phase/Stage,Activity (Title),Activity Description,Motivation,Process,Outcome,Participants"

How to use

AutoDoc is an MCP stdio server that monitors a Git repository and generates structured, daily CSV reports by analyzing commits. It converts commit history into business-oriented summaries across configurable columns, producing CSV rows that can be used for progress tracking, status reporting, or automated documentation workflows. Use the server by running it through a compatible MCP client (e.g., an editor integration or automation pipeline) which communicates via stdio and sends prompts like “Generate the report for my commits this week and save it.” The server uses environment-driven configuration to tailor the repository path, ownership, culture, output location, reporting columns, and the summarization rules, enabling customized, repeatable reporting workflows. Tools available include: environment-configured REPORT_COLUMNS_TITLES to shape CSV headers, RULES to steer summarization and filtering, and PROJECT_METADATA to provide context within reports.

How to install

Prerequisites:

.NET SDK installed (recommended version compatible with AutoDocMcpServer).
Access to the repository that contains AutoDocMcpServer project.

Installation steps:

Install .NET from https://dotnet.microsoft.com/download.
Clone the MCP server repository (or download the source): git clone https://github.com/yourorg/AutoDocMcpServer.git
Build or run the project: cd AutoDocMcpServer dotnet build
Run directly for testing
dotnet run --project AutoDocMcpServer/AutoDocMcpServer.csproj
Alternatively configure MCP client to launch via stdio using the provided example configuration and ensure environment variables are set as needed.
Ensure the environment variables REPOSITORY_PATH, OWNER_EMAIL, OWNER_NAME, CULTURE, OUTPUT_PATH, REPORT_COLUMNS_TITLES, RULES, and PROJECT_METADATA are defined for proper operation.

Additional notes

Tips and common issues:

Update RULES to reflect your team's commit style to improve summarization relevance.
Ensure REPOSITORY_PATH points to a clean working tree for accurate reports.
If OUTPUT_PATH does not exist, create it or ensure the process has write permissions.
CULTURE should align with your desired locale for formatting; e.g., en-US or pt-BR.
REPORT_COLUMNS_TITLES must match the desired CSV header layout used by downstream templates.
The MCP client communicates via stdio; ensure your integration correctly handles prompt/response formatting and potential buffering.

Related MCP Servers

mem0

✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.

knowledgegraph

MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with multiple storage backends and fuzzy search

mcpbi

PowerBI MCP server to give LLM clients (Claude, GH Copilot,etc) context from locally running PowerBI Desktop instances.

finance

LLM-powered MCP server for building financial deep-research agents, integrating web search, Crawl4AI scraping, and entity extraction into composable analysis flows.

website-publisher

AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.

mcp -graph-api

Model-context-protocol (MCP) server for the Microsoft Graph API in C#