Dig

Name: Dig
Author: nakishiyaman

by nakishiyamancommunityv0.4.1

This MCP server provides tools for AI-powered code archaeology, enabling users to explore git blame, file history, contributor patterns, and co-change analysis.

From the registry: MCP server for code archaeology: git blame, file history, contributors, and co-change analysis

GitHub Repository

Install & configure

Prerequisites

required
Install mcp-server-dig globally
Install the mcp-server-dig binary from npm.
```
$ npm install -g mcp-server-dig
```
https://www.npmjs.com/package/mcp-server-dig

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `dig` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install mcp-server-dig globally** — Install the mcp-server-dig binary from npm. Run: `npm install -g mcp-server-dig` (https://www.npmjs.com/package/mcp-server-dig)

Canonical MCP server config (stdio transport):
- command: `mcp-server-dig`
- args: []
- optional environment variables:
  - `DIG_LOG_LEVEL`: Log level; set to 'debug' for git command timing and cache hit/miss logs. (example: `info`)

Note: Git archaeology server: blame, history, contributor patterns, co-change analysis.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Git archaeology server: blame, history, contributor patterns, co-change analysis.

Tools (16)

git_review_prep

PR review briefing with risk flags, reviewer suggestions, and missing file detection

git_why

Code archaeology narrative — explains why code exists by combining blame, commits, contributors, and co-changes

git_file_risk_profile

Multi-dimensional risk assessment for a single file

git_repo_health

Repository-wide health summary

git_code_ownership_changes

Compare code ownership before/after a date boundary — detects owner handoffs, bus factor changes, knowledge transfer patterns

git_impact_analysis

Blast radius analysis for a file or directory — combines co-change networks, contributor overlap, and directory coupling

git_knowledge_loss_risk

Assess knowledge loss risk per contributor — identifies directories where a single person owns most of the code (bus factor = 1) and estimates recovery cost

git_trend_analysis

Analyze trends over time by comparing metrics across multiple time periods — tracks whether hotspot count, code churn, contributor count, or commit activity is improving, stable, or worsening

git_refactor_candidates

Identify and rank refactoring candidates across the repository using 5-dimension risk assessment (change frequency, code churn, knowledge concentration, coupling, staleness)

git_release_comparison

Compare repository metrics between two git refs (tags, branches, commits) — shows how hotspots, churn, contributor count, and bus factor changed between releases