gitwhy-mcp
GitWhy MCP Server
The shared AI context engine for git — save, search, and share the reasoning behind code changes.
GitWhy captures the why behind every commit: reasoning, decisions, and trade-offs. This MCP server makes GitWhy's tools available to AI coding agents like Claude, Cursor, Windsurf, and VS Code Copilot.
Install
npm (recommended for MCP clients)
npm install -g gitwhy-mcpHomebrew (macOS/Linux)
brew install gitwhy-cli/tap/git-whyScoop (Windows)
scoop bucket add gitwhy https://github.com/quanng28/gitwhy-scoop-bucket
scoop install git-whyRelated MCP server: Selvedge
MCP Configuration
Claude Desktop / Claude Code
Add to your MCP config (~/.claude/settings.json or Claude Desktop settings):
{
"mcpServers": {
"gitwhy": {
"command": "gitwhy-mcp",
"args": []
}
}
}Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"gitwhy": {
"command": "npx",
"args": ["-y", "gitwhy-mcp"]
}
}
}VS Code
Add to .vscode/mcp.json:
{
"servers": {
"gitwhy": {
"command": "npx",
"args": ["-y", "gitwhy-mcp"]
}
}
}Tools
Tool | Description |
| Save development context (reasoning, decisions, trade-offs) for the current session |
| Retrieve a saved context by its ID |
| Search saved contexts by keyword or natural language query |
| Browse saved contexts by domain/topic hierarchy |
| Check setup state, pending commits, and sync status |
| Upload local contexts to the cloud (private) |
| Share synced contexts with your team |
| Post context summary as a GitHub PR comment |
Authentication
For cloud features (sync, publish, PR comments), you need a GitWhy API key:
Sign up at app.gitwhy.dev
Get your API key at app.gitwhy.dev/dashboard/api-keys
For local CLI: run
git why setupto authenticateFor remote (Smithery/Glama): paste your API key when prompted
Links
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
Related MCP Servers
- AlicenseAqualityCmaintenanceArchitectural memory layer for AI coding. Automatically extracts decisions, detects security gaps, and analyzes git history from your codebase in one command.328 npm2MIT
- AlicenseAqualityAmaintenanceChange tracking for AI-era codebases. AI agents call it to log structured change events (entity + diff + reasoning) before the session ends, then query history with diff, blame, history, changeset, and search. Captures the intent that would otherwise evaporate.8433 PyPI23MIT
- AlicenseAqualityAmaintenanceLocal-first memory layer for AI coding agents — captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.17823MIT
- AlicenseAqualityDmaintenanceEnables AI coding agents to persist structured long-term memory (gotchas, architecture, API notes) in a .context folder and sync across devices and agents via Git.48 npm19MIT