Analyzes GitHub repositories to provide architecture, file roles, execution flows, system design Q&A, and structured agent context.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@revibe-mcp Analyze the architecture of github.com/facebook/react"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
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.
Related MCP server: Gitingest-MCP
pip install revibe-mcp
revibe-mcp-auth login{
"mcpServers": {
"revibe": {
"command": "revibe-mcp"
}
}
}Client | Config location |
Claude Desktop |
|
Claude Code |
|
Cursor | Settings > MCP Servers > Add |
Windsurf | MCP config in settings |
Two options:
Option A: Browser login (recommended)
# Node.js
npx revibe-mcp-auth login
# Python
revibe-mcp-auth loginOpens 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:
{
"mcpServers": {
"revibe": {
"command": "npx",
"args": ["revibe-mcp"],
"env": {
"REVIBE_API_KEY": "rk_live_your_key_here"
}
}
}
}Tool | Description |
| Log in via browser — one-time setup |
| Submit a GitHub repo for analysis (auto-detects from git remote) |
| Check progress of an analysis job |
| Architecture, modules, patterns overview |
| Drill into architecture, file_roles, system_design_qa, etc. |
| Full structured JSON optimized for AI agents |
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.
# Node.js
npx revibe-mcp-auth login # Log in via browser
npx revibe-mcp-auth status # Show current auth status
npx revibe-mcp-auth logout # Remove saved credentials
# Python
revibe-mcp-auth login
revibe-mcp-auth status
revibe-mcp-auth logoutIf you use Claude Code, you can install Revibe as a slash command skill instead of (or in addition to) the MCP server:
# Copy the skill file
mkdir -p ~/.claude/skills/revibe
curl -o ~/.claude/skills/revibe/SKILL.md \
https://raw.githubusercontent.com/selvatuple/revibe-mcp/main/skills/claude-code/SKILL.mdThen use /revibe or /revibe github.com/user/repo inside Claude Code.
The skill file is also available at skills/claude-code/SKILL.md.
Method | Install |
npm (zero install) |
|
PyPI |
|
MCP Registry | registry.modelcontextprotocol.io — search "revibe" |
Claude Code Skill | Copy |
MIT
Submit a GitHub repository for Revibe analysis. Analyzes architecture, file roles, execution flows, system design Q&A, and more. If no URL is provided, auto-detects from the current git remote. Analysis takes 3-7 minutes for most repos.
Inputs: reanalyze, github_url.
Check the status of a Revibe analysis job.
Inputs: job_id (required).
Get the full agent context JSON for a completed analysis. This is a structured format optimized for AI agents, containing file index, dependency graph, architecture layers, call chains, constraints, design decisions, and database schema. Save the output to agent_context.json for persistent codebase understanding.
Inputs: job_id (required).
Get a specific analysis section from a completed Revibe analysis.
Available sections:
technical_architecture (or "architecture") — system layers, technologies, diagrams
file_roles — what each file does, importance, dependencies
system_design_qa — interview-style Q&A about design decisions
story_flow (or "execution_flows") — how the app starts up and handles requests
database_schema (or "database") — tables, relationships, ER diagrams
concepts_explanation (or "concepts") — key patterns and concepts used
modules — logical groupings of files
business_logic — core domain logic and rules
flow_implementation — detailed execution flow code traces
Inputs: job_id (required), section (required).
Get a condensed summary of a completed Revibe analysis. Shows architecture pattern, language, file count, key modules, and available sections.
Inputs: job_id (required).
Log in to Revibe via browser. Opens a browser window for authentication. After logging in and clicking Authorize, the API key is saved locally so all other Revibe tools work automatically.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a distinct role: login for authentication, analyze_repo for submission, check_status for job monitoring, and three retrieval tools with clear separation of scope. get_summary, get_section, and get_agent_context serve different granularities of output, preventing confusion.
Most tools follow a clear verb_noun pattern (analyze_repo, check_status, get_summary, get_section, get_agent_context). The exception is revibe_login, which places a brand prefix before a verb and does not match the conventional verb-first structure, creating a minor inconsistency.
With 6 tools, the server is well-scoped for its purpose: authentication, analysis submission, status polling, and result retrieval. This is an appropriate size that covers the workflow without redundancy or unnecessary bloat.
The tool set covers the complete lifecycle of a Revibe analysis: login, submit repository, check progress, and retrieve results in multiple formats (summary, sections, and full agent context). No critical steps are missing for the intended use case, and the output options are sufficient for both human and agent consumption.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Repo intel for AI coding agents: overview, PRs, contributors, hot files, CI, deps. Remote MCP.
GitHub Copilot MCP: code, repo, PR, workflow tools for AI assistants.
Ask any GitHub repository a question. Get source-backed answers.
