Skip to main content
Glama

Atlas-G Protocol

Agentic Portfolio System - A compliance-grade MCP server that serves as both human and machine-readable portfolio.

Python FastAPI Cloud Run MCP

šŸŽÆ 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: resume-mcp

šŸ”’ 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.txt knowledge graph before responding.

šŸ—ļø Architecture

ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│                   Cloud Run Instance                 │
ā”œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¤
│  ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”    ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā” │
│  │  React Frontend │◄──►│  FastAPI Backend        │ │
│  │  (Terminal UI)  │    │  - Agent Core           │ │
│  ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜    │  - Governance Layer     │ │
│                         │  - MCP Server           │ │
│                         ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜ │
│                                     │               │
│                         ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā” │
│                         │  Tools                  │ │
│                         │  - query_resume         │ │
│                         │  - verify_employment    │ │
│                         │  - audit_project        │ │
│                         ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜ │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜

šŸš€ 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_KEY

Run Locally

# Start the server
uvicorn backend.main:application --reload --port 8080

# Open http://localhost:8080

Run Tests

pytest backend/tests/ -v

šŸ”§ 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

query_resume

Semantic search over resume knowledge graph

verify_employment

Cross-reference employment claims

audit_project

Deep-dive into project architecture

ā˜ļø 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

šŸ“ Project Structure

Atlas-G Protocol/
ā”œā”€ā”€ backend/
│   ā”œā”€ā”€ __init__.py
│   ā”œā”€ā”€ main.py          # FastAPI application
│   ā”œā”€ā”€ agent.py         # Thought-Action loop
│   ā”œā”€ā”€ governance.py    # Hallucination mitigation
│   ā”œā”€ā”€ mcp_server.py    # FastMCP wrapper
│   ā”œā”€ā”€ config.py        # Settings management
│   └── tools/
│       ā”œā”€ā”€ resume_rag.py
│       └── verification.py
ā”œā”€ā”€ frontend/            # React UI (Phase 3)
ā”œā”€ā”€ data/
│   └── resume.txt       # Knowledge graph source
ā”œā”€ā”€ Dockerfile
ā”œā”€ā”€ pyproject.toml
└── mcp_config.json

šŸ”’ Security

  • CSP Headers: frame-ancestors 'self' https://dev.to https://*.dev.to

  • Governance Layer: All AI responses validated against resume data

  • PII Detection: Automatic filtering of sensitive information

  • Jailbreak Protection: Pattern-based detection and blocking

šŸ“„ License

MIT License - See LICENSE for details.

šŸ“¢ Credits

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

–Maintainers
–Response time
0dRelease cycle
2Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    C
    maintenance
    An MCP server that provides a structured API for AI agents to query a person's resume, including profile, projects, writing, and gated access to experience and skills.
    Last updated
  • A
    license
    -
    quality
    D
    maintenance
    Exposes 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.
    Last updated
    MIT

View all related MCP servers

Related MCP Connectors

  • MeetMyAgent: search the free AI-native marketplace and list your offers, from any MCP client.

  • Agent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.

  • Give AI agents real phone numbers, messages, and voice calls via MCP.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MichaelWeed/atlas-g-protocol'

If you have feedback or need assistance with the MCP directory API, please join our Discord server