Rene Fichtmueller f2470f3e56 feat: initial release — AI-powered network intelligence platform

PeerCortex unifies PeeringDB, RIPE Stat, bgproutes.io, RIPE Atlas,
Route Views, IRR, RPKI, and CAIDA into a single AI-queryable MCP Server
for network engineers. Powered by local Ollama.

Core capabilities:
- 34 MCP tools for network intelligence
- 11 data sources unified
- ASPA validation engine (RFC 9582) with leak detection
- Peering partner discovery with AI-ranked matches
- BGP analysis and anomaly detection
- RPKI monitoring and compliance reports
- Latency/traceroute via RIPE Atlas
- Transit analysis and cost comparison
- IX traffic statistics
- AS topology mapping
- ASPA object generator and simulator
- 100% local AI — no cloud dependencies

2026-03-26 07:26:14 +13:00

2.4 KiB

Raw Blame History

Setup Guide

Prerequisites

Node.js 20+ (LTS recommended)
Ollama installed and running locally
Docker (optional, for containerized deployment)

Quick Start

1. Install Ollama

# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.com/install.sh | sh

# Pull a recommended model
ollama pull llama3.1

2. Install PeerCortex

# Clone the repository
git clone https://github.com/peercortex/peercortex.git
cd peercortex

# Install dependencies
npm install

# Copy environment configuration
cp .env.example .env

# Build
npm run build

# Start the MCP server
npm start

3. Configure Claude Code

Add PeerCortex to your Claude Code MCP configuration:

{
  "mcpServers": {
    "peercortex": {
      "command": "node",
      "args": ["/path/to/peercortex/dist/mcp-server/index.js"],
      "env": {
        "OLLAMA_BASE_URL": "http://localhost:11434",
        "OLLAMA_MODEL": "llama3.1"
      }
    }
  }
}

4. Docker Setup (Alternative)

# Start PeerCortex with Ollama
docker compose up -d

# Pull the AI model inside the Ollama container
docker exec peercortex-ollama ollama pull llama3.1

Configuration Reference

See .env.example for all available configuration options.

Variable	Default	Description
`OLLAMA_BASE_URL`	`http://localhost:11434`	Ollama API endpoint
`OLLAMA_MODEL`	`llama3.1`	LLM model for analysis
`PEERINGDB_API_KEY`	(empty)	Optional PeeringDB API key
`RIPE_STAT_SOURCE_APP`	`peercortex`	RIPE Stat source app identifier
`ROUTINATOR_URL`	`http://localhost:8323`	Routinator RPKI validator URL
`CACHE_DB_PATH`	`./peercortex-cache.db`	SQLite cache file path
`CACHE_TTL_SECONDS`	`3600`	Default cache TTL
`MCP_TRANSPORT`	`stdio`	Transport protocol (stdio/sse)
`LOG_LEVEL`	`info`	Logging level

Optional: PeeringDB API Key

PeerCortex works without a PeeringDB API key, but you'll hit rate limits faster. To get a free API key:

Create an account at peeringdb.com
Go to your profile settings
Generate an API key
Add it to your .env file

Optional: Local RPKI Validator

For faster RPKI validation, run Routinator locally:

# Via Docker
docker run -d --name routinator -p 8323:8323 nlnetlabs/routinator

# Or uncomment the routinator service in docker-compose.yml

2.4 KiB Raw Blame History