Revibe Mcp

io.github.selvatuplePublished by GitHub account selvatuplev0.1.1Updated Oct 24, 2026

Analyze any codebase — get architecture, file roles, execution flows, and agent context.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Revibe MCP lets an AI assistant submit GitHub repositories for analysis and retrieve architecture, file roles, execution flows and agent-ready context.

What you can do
Submit a GitHub repository for analysis, with auto-detection from the local git remote, and check the progress of the analysis job. Retrieve an overview of architecture, modules and patterns. Drill into individual sections such as architecture, file roles and system design Q&A. Fetch a full structured JSON context optimized for AI agents. Log in through the browser for one-time setup.
When to use it
Useful when you want an assistant to explain an unfamiliar codebase, summarize its architecture, or produce structured context for agent workflows without reading every file yourself. Suited to GitHub-hosted projects you are willing to send to a third-party analysis service.
Requirements
Runs locally over stdio via npx or a pip install. Needs Node.js or Python, network access, and a Revibe account. Authentication is either browser login, which saves credentials to a local config file, or an API key supplied through the REVIBE_API_KEY environment variable.
Before you install
Repository contents are sent to the Revibe service for analysis, so avoid private or sensitive code unless you accept that. The API key is a secret; the browser login stores credentials on disk. The README also suggests downloading a skill file with curl, which runs outside the MCP server.

Installation

In SourceWeft

  1. Open Revibe Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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:

json
{  "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)

bash
pip install revibe-mcprevibe-mcp-auth login
json
{  "mcpServers": {    "revibe": {      "command": "revibe-mcp"    }  }}

Where to add the config

ClientConfig location
Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json
Claude Code.mcp.json in your project root
CursorSettings > MCP Servers > Add
WindsurfMCP config in settings

Auth

Two options:

Option A: Browser login (recommended)

bash
# Node.jsnpx revibe-mcp-auth login
# Pythonrevibe-mcp-auth login

Opens your browser — sign up or log in, click "Authorize". API key saved automatically to ~/.config/revibe/credentials.json.

Option B: Manual API key

Get a key from app.revibe.codes/settings, then pass it via env:

json
{  "mcpServers": {    "revibe": {      "command": "npx",      "args": ["revibe-mcp"],      "env": {        "REVIBE_API_KEY": "rk_live_your_key_here"      }    }  }}

Tools

ToolDescription
revibe_loginLog in via browser — one-time setup
analyze_repoSubmit a GitHub repo for analysis (auto-detects from git remote)
check_statusCheck progress of an analysis job
get_summaryArchitecture, modules, patterns overview
get_sectionDrill into architecture, file_roles, system_design_qa, etc.
get_agent_contextFull structured JSON optimized for AI agents

Usage

Once configured, just ask your AI assistant:

  • "Analyze this repo with Revibe"
  • "What's the architecture of github.com/user/repo?"
  • "Get the agent context for this codebase"

The tools handle auto-detection, polling, and structured output automatically.

CLI Commands

bash
# Node.jsnpx revibe-mcp-auth login     # Log in via browsernpx revibe-mcp-auth status    # Show current auth statusnpx revibe-mcp-auth logout    # Remove saved credentials
# Pythonrevibe-mcp-auth loginrevibe-mcp-auth statusrevibe-mcp-auth logout

Claude Code Skill

If you use Claude Code, you can install Revibe as a slash command skill instead of (or in addition to) the MCP server:

bash
# Copy the skill filemkdir -p ~/.claude/skills/revibecurl -o ~/.claude/skills/revibe/SKILL.md \  https://raw.githubusercontent.com/selvatuple/revibe-mcp/main/skills/claude-code/SKILL.md

Then use /revibe or /revibe github.com/user/repo inside Claude Code.

The skill file is also available at skills/claude-code/SKILL.md.

Packages & Distribution

MethodInstall
npm (zero install)npx revibe-mcp
PyPIpip install revibe-mcp
MCP Registryregistry.modelcontextprotocol.io — search "revibe"
Claude Code SkillCopy skills/claude-code/SKILL.md to ~/.claude/skills/revibe/

License

MIT

Source: README.md at commit 378c387

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts