RepoRipple MCP server

RepoRipple

<!-- mcp-name: io.github.adiarora06/reporipple -->

Know what a code change can break before you merge it.

RepoRipple is a local-first change-impact analyzer for engineers and coding agents. It builds a lightweight dependency graph from a repository, reads the current Git diff, traces reverse dependencies, recommends relevant tests, and emits a review-ready Markdown or JSON report.

The deterministic analyzer requires no API key, hosted service, source upload, or framework integration. An optional, explicitly requested OpenRouter explanation can turn its anonymized evidence into a short narrative without changing the underlying analysis.

Why RepoRipple?

Code graphs explain how a repository is connected. RepoRipple applies that graph to the change in front of you:

• Which files depend on the code I changed?
• How far does the blast radius travel?
• Which tests are most relevant?
• Did I touch authentication, payments, deployment, or another sensitive area?
• Should this pull request be blocked for additional review?
• What structured context should I give a coding agent?

Quick start

git clone https://github.com/adiarora06/RepoRipple.git
cd RepoRipple
python -m venv .venv
source .venv/bin/activate
pip install -e .

# Analyze staged, unstaged, and untracked changes in another repository.
reporipple /path/to/repository

# Compare a feature branch with main.
reporipple /path/to/repository --base main

# Generate machine-readable context for an agent or automation.
reporipple /path/to/repository --base main --format json --output impact.json

# Fail CI when a change reaches high risk.
reporipple . --base origin/main --fail-on high

# Audit the exact anonymized OpenRouter request without sending it.
reporipple . --base origin/main --explain-preview

GitHub Action

Add RepoRipple to a pull-request workflow to create Markdown and JSON impact reports and append the Markdown report to the GitHub job summary:

name: RepoRipple

on:
  pull_request:

permissions:
  contents: read

jobs:
  impact:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@d23441a48e516b6c34aea4fa41551a30e30af803 # v6
        with:
          fetch-depth: 0
          persist-credentials: false
      - id: reporipple
        uses: adiarora06/RepoRipple@24e4e431c241b9adb76e8735640a53ab8d1c3248
        with:
          base: ${{ github.event.pull_request.base.sha }}
      - uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
        with:
          name: reporipple-impact
          path: |
            ${{ steps.reporipple.outputs.markdown-report }}
            ${{ steps.reporipple.outputs.json-report }}

The Action accepts path, base, max-depth, fail-on, and reports-directory. It outputs markdown-report, json-report, and risk-level. For reproducible builds, pin RepoRipple to a release commit SHA and use fetch-depth: 0 so the requested base revision is available.

This repository's own pull-request workflow demonstrates a fork-safe commenting design. Analysis runs with read-only contents access. A separate job updates one stable RepoRipple comment only for branches in the same repository; fork pull requests keep their report in the job summary and downloadable artifact without receiving a write-capable token.

Coding-agent tools (MCP)

RepoRipple can expose the same deterministic analysis to Codex, OpenCode, Cursor, Claude Code, and VS Code over a local, read-only MCP server. From a source checkout:

uv run reporipple mcp --root /path/to/allowed/workspace

After the package is published to PyPI, agent configurations can launch it without a clone:

uvx reporipple mcp --root /path/to/allowed/workspace

Shortened. The full README is on GitHub.