atlas-g-protocol
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Atlas-G Protocol
Agentic Portfolio System - A compliance-grade MCP server that serves as both human and machine-readable portfolio.
🎯 Overview
Atlas-G Protocol transforms a traditional developer portfolio into an autonomous agent that demonstrates compliance-grade engineering in real-time. Instead of reading about experience with "strict state management" and "hallucination mitigation," users interact with an agent that actively demonstrates these capabilities.
Key Features
MCP Server: Machine-readable portfolio accessible by AI development environments
Governance Layer: Real-time hallucination mitigation via knowledge graph validation
Live Audit Log: Streams internal compliance checks to the UI
WebSocket Streaming: Real-time "Thought-Action" loop visualization
CSP Headers: Configured for DEV.to iframe embedding
Related MCP server: personal-resume-agent
🔒 Privacy & Data Governance
The Atlas-G Protocol follows a "Private-by-Design" pattern to ensure sensitive career data isn't leaked in public repositories:
Template Pattern: All proprietary information (work history, PII) is stored in
data/resume.txt, which is explicitly excluded from the repository via.gitignore.resume.template.txt: A sanitized template is provided for open-source users to populate with their own data.
Hallucination Mitigation: The agent's governance layer validates every claim against the local
resume.txtknowledge graph before responding.
🏗️ Architecture
┌─────────────────────────────────────────────────────┐
│ Cloud Run Instance │
├─────────────────────────────────────────────────────┤
│ ┌─────────────────┐ ┌─────────────────────────┐ │
│ │ React Frontend │◄──►│ FastAPI Backend │ │
│ │ (Terminal UI) │ │ - Agent Core │ │
│ └─────────────────┘ │ - Governance Layer │ │
│ │ - MCP Server │ │
│ └───────────┬─────────────┘ │
│ │ │
│ ┌───────────▼─────────────┐ │
│ │ Tools │ │
│ │ - query_resume │ │
│ │ - verify_employment │ │
│ │ - audit_project │ │
│ └─────────────────────────┘ │
└─────────────────────────────────────────────────────┘🚀 Quick Start
Prerequisites
Python 3.11+
Google Cloud API Key (for Gemini)
Installation
# Clone the repository
cd Atlas-G\ Protocol
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -e ".[dev]"
# Copy environment template
cp .env.example .env
# Edit .env with your GOOGLE_API_KEYRun Locally
# Start the server
uvicorn backend.main:application --reload --port 8080
# Open http://localhost:8080Run Tests
pytest backend/tests/ -v🔧 MCP Integration
Connect your AI development environment to the Atlas-G MCP server:
{
"mcpServers": {
"atlas-g-protocol": {
"command": "python",
"args": ["-m", "backend.mcp_server"]
}
}
}Available Tools
Tool | Description |
| Semantic search over resume knowledge graph |
| Cross-reference employment claims |
| Deep-dive into project architecture |
☁️ Deploy to Cloud Run
gcloud run deploy atlas-g-portfolio \
--source . \
--allow-unauthenticated \
--region us-central1 \
--labels dev-tutorial=devnewyear2026 \
--set-env-vars GOOGLE_API_KEY=your_key_here📁 Project Structure
Atlas-G Protocol/
├── backend/
│ ├── __init__.py
│ ├── main.py # FastAPI application
│ ├── agent.py # Thought-Action loop
│ ├── governance.py # Hallucination mitigation
│ ├── mcp_server.py # FastMCP wrapper
│ ├── config.py # Settings management
│ └── tools/
│ ├── resume_rag.py
│ └── verification.py
├── frontend/ # React UI (Phase 3)
├── data/
│ └── resume.txt # Knowledge graph source
├── Dockerfile
├── pyproject.toml
└── mcp_config.json🔒 Security
CSP Headers:
frame-ancestors 'self' https://dev.to https://*.dev.toGovernance Layer: All AI responses validated against resume data
PII Detection: Automatic filtering of sensitive information
Jailbreak Protection: Pattern-based detection and blocking
📄 License
MIT License - See LICENSE for details.
📢 Credits
Audio: Emergency Alarm.wav by Mozfoo (CC0)
This server cannot be deployed
Maintenance
Related MCP Connectors
The first portfolio AI agents can hire. Profile, products, pricing and briefs over MCP.
The headless professional network: create a profile, then let your agent find you matches via MCP.
Public portfolio MCP for resume, services, availability, project evidence, and introductions.
Maintain your CV with your agent. Review changes, then share one record as web, PDF and open data.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAI job search, resume builder, and career advice via MCP2MIT
- AlicenseNot gradedqualityDmaintenanceExposes a personalized AI agent that reads your resume and provides intelligent responses about your professional background through a standardized MCP server interface with RAG capabilities.MIT
- AlicenseNot gradedqualityDmaintenancePublish yourself as a remote MCP server, exposing your résumé via tools so company agents can evaluate and contact you.MIT
- AlicenseAqualityDmaintenanceA resume MCP server that enables AI agents to search work history by keyword or meaning, retrieve detailed company info, and send scheduling emails, turning a static resume into interactive tools.3MIT