Analyze code history and authorship with git blame, file tracking, and contributor insights. Built for developers investigating legacy code, understanding change patterns, and identifying subject-matter experts.
io.github.nakishiyaman/dig
Local install
STDIO
No auth required
How models use it and what it is built for.
Analyze code history and authorship with git blame, file tracking, and contributor insights. Built for developers investigating legacy code, understanding change patterns, and identifying subject-matter experts.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Nakishiyaman Dig.
Paste any of these into Agent Studio after connecting Nakishiyaman Dig.
Common questions about connecting and running Nakishiyaman Dig.
What does the dig MCP server do?
It provides code archaeology capabilities including git blame (line-by-line authorship), file history tracking, contributor analysis, and co-change detection to help you understand how code has evolved and who modified it.
Does dig require git to be installed?
Yes, dig operates on git repositories, so you need git installed and initialized in your project. It reads git history directly from your .git directory.
Can dig analyze files outside my git repository?
No, dig only works on files tracked in git. It relies on git history, so untracked or non-git files cannot be analyzed.
What is co-change analysis and why is it useful?
Co-change analysis identifies files that are frequently modified together in the same commits. This reveals hidden dependencies and helps you understand which parts of the codebase are tightly coupled.
How do I install and run the dig MCP server?
Install with `npx mcp-server-dig@0.4.1`. It runs over stdio transport, so connect it to your MCP client (like Claude Desktop) and point it to a git repository to start querying history and authorship data.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams