
Revibe Mcp
This connects your MCP client to Revibe's codebase analysis API. Point it at any GitHub repo and get back structured breakdowns: architecture patterns, file role classifications, execution flows, and system design Q&A formatted for agent consumption. Ships with tools for submitting repos, polling job status, and retrieving sections of the analysis report. Auth happens via browser login or manual API key. Works with zero install via npx, or install through pip. Also available as a Claude Code slash command skill if you prefer that workflow. Useful when onboarding to unfamiliar codebases or feeding architectural context into long running AI sessions.
- tools
- 6
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Mar 16, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
revibe_loginLog in via browser — one-time setup
Log in via browser — one-time setup
No parameter schema in public metadata yet.
analyze_repoSubmit a GitHub repo for analysis (auto-detects from git remote)
Submit a GitHub repo for analysis (auto-detects from git remote)
No parameter schema in public metadata yet.
check_statusCheck progress of an analysis job
Check progress of an analysis job
No parameter schema in public metadata yet.
get_summaryArchitecture, modules, patterns overview
Architecture, modules, patterns overview
No parameter schema in public metadata yet.
get_sectionDrill into architecture, file_roles, system_design_qa, etc.
Drill into architecture, file_roles, system_design_qa, etc.
No parameter schema in public metadata yet.
get_agent_contextFull structured JSON optimized for AI agents
Full structured JSON optimized for AI agents
No parameter schema in public metadata yet.
Sponsors
Configuration
REVIBE_API_KEYsecretRevibe API key (optional — you can also use the revibe_login tool for browser-based auth)
Readme
revibe-mcp
MCP server for Revibe codebase analysis. Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.
Analyze any GitHub repo — get architecture, file roles, execution flows, system design Q&A, and structured agent context.
Quick Start (Node.js — zero install)
Add to your MCP client config:
{
"mcpServers": {
"revibe": {
"command": "npx",
"args": ["revibe-mcp"]
}
}
}
Then ask your AI assistant to "log in to Revibe" — it will open your browser for a one-time signup.
Quick Start (Python)
pip install revibe-mcp
revibe-mcp-auth login
{
"mcpServers": {
"revibe": {
"command": "revibe-mcp"
}
}
}
Where to add the config
| Client | Config location |
|---|---|
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Code | .mcp.json in your project root |
| Cursor | Settings > MCP Servers > Add |
| Windsurf | MCP config in settings |
Auth
Two options:
Option A: Browser login (recommended)
# Node.js
npx revibe-mcp-auth login
Details
- Repository
- github.com/selvatuple/revibe-mcp
- Category
- AI & LLM Tools
- Package
revibe-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active