Wisegit

@Sandip124

About Wisegit

MCP server that extracts decision intent from git history and protects intentional code from AI modification.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "wisegit": {
      "command": "npx",
      "args": [
        "-y",
        "@sandip124/wisegit",
        "serve"
      ]
    }
  }
}

Tools

Get the decision manifest for a file — shows freeze scores, intent history, and recovery levels for all tracked functions. Call this BEFORE editing any file.

Get the freeze score and signal breakdown for a specific function. Shows why a function is frozen/stable/open.

Search past decisions by keyword. Finds intent history across the entire repository.

Request an override for a FROZEN or STABLE function so it can be modified. The user MUST approve this action. Provide a clear reason why the override is needed. The override is recorded in the audit trail permanently.

Get the full chronological decision timeline for a specific function. Shows every event: creation, changes, overrides, issue enrichments.

Get functions in a file where the original decision rationale may be unrecoverable (primary author inactive, timeline gaps). These need extra caution.

Get branch merge history — what branches were merged and what they changed. Useful for understanding migrations and cross-platform decisions.

Extract decision intent for a function's NOISE commits using the host LLM (no Ollama needed). Call this when a function has events with LOW or missing intent to recover the 'why' behind changes.

Overview

What is Wisegit?

Wisegit is a local MCP server that extracts decision intent from git history, so AI agents respect intentional code rather than treating all code equally. It indexes commits, computes per-function “freeze scores,” and serves decision manifests—marking functions as frozen, stable, or open—before any file edit.

How to use Wisegit?

Run npx @sandip124/wisegit setup in any repository—zero configuration. After indexing, AI agents call MCP tools such as get_file_decisions to retrieve decision manifests, and create_override to override frozen functions with user approval in Claude Code.

Key features of Wisegit

Zero config setup with a single command
SQLite database (no Docker or external services)
Team support via .wisegit/ directory tracked by git
AI-era commit origin detection (human, AI reviewed, AI unreviewed)
Theory holder tracking per function (healthy / fragile / critical)
HTML codebase health report (wisegit report)
Grounded in 12 published software engineering papers

Use cases of Wisegit

Prevent AI agents from removing manually‑tested workarounds (e.g., sleep(350) for race conditions)
Identify functions lacking active theory holders to mitigate institutional knowledge loss
Safely modify code by respecting frozen/stable/open zones with auditable overrides
Search past decisions across the entire git history for context during code reviews

FAQ from Wisegit

What are the runtime requirements?

Only a local SQLite database—no Docker, PostgreSQL, or any external services needed.

How does Wisegit classify commits?

It parses diffs at the AST level using Tree‑sitter for C#, TypeScript, JavaScript, Python, Go, and Rust, then labels commits as STRUCTURED, DESCRIPTIVE, or NOISE.

What is a freeze score?

A 0–1 score per function derived from seven signal categories including git history, issue enrichment, code structure, test signals, and structural importance.

How does team collaboration work?

The .wisegit/ directory is tracked by git; JSONL files within it merge cleanly, enabling shared override audit trails and decision histories.

What MCP tools does Wisegit expose?

Eight tools: get_file_decisions, get_freeze_score, get_function_history, get_theory_gaps, get_branch_context, search_decisions, create_override, and extract_intent.

Frequently asked questions