About Arcology Knowledge Node
Arcology Knowledge Node is a read-only MCP server for AI agents querying an engineering knowledge base about Arcology One, a speculative city designed for 10 million people. It provides search and retrieval across eight domains, alongside open questions and quantitative parameters.
Key features
- 01Search knowledge with filters
- 02Retrieve full knowledge entries
- 03List eight domains and their statistics
- 04Find unanswered engineering questions
- 05Retrieve quantitative parameters
Use cases
- 01Explore Arcology One engineering topics
- 02Find unanswered questions in a domain
- 03Check quantitative parameters for consistency
MCP support
It exposes read-only search and retrieval tools for the Arcology One engineering knowledge base to MCP clients. The tools also provide domain statistics, open questions, and quantitative parameters.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://arcology-mcp.fly.dev/mcpclaude mcp add --transport http yourlifewithai https://arcology-mcp.fly.dev/mcp{"mcpServers":{"yourlifewithai":{"type":"http","url":"https://arcology-mcp.fly.dev/mcp"}}}Open in Cursor{"servers":{"yourlifewithai":{"type":"http","url":"https://arcology-mcp.fly.dev/mcp"}}}Open in VS Code{"mcpServers":{"yourlifewithai":{"type":"http","url":"https://arcology-mcp.fly.dev/mcp"}}}{"mcpServers":{"yourlifewithai":{"serverUrl":"https://arcology-mcp.fly.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
9| Parameter | Type | Required | Description |
|---|---|---|---|
| slug | string | Yes | |
| domain | string | Yes |
Details
From the project READMEArcology Knowledge Node — MCP Server
Read-only MCP server for AI agents to query the Arcology One engineering knowledge base.
Tools
| Tool | Purpose |
|---|---|
read_node(domain, slug) | Retrieve full knowledge entry |
search_knowledge(query, ...) | Full-text search with filters |
list_domains() | All 8 domains with stats |
get_open_questions(domain?, limit?) | Unanswered engineering questions |
get_entry_parameters(domain?, parameter_name?) | Quantitative parameters for consistency checking |
get_domain_stats() | Aggregate platform statistics |
Local Development
# Install dependencies
pip install -e .
# Run with stdio (for Claude Desktop)
python server.py
# Run with Streamable HTTP (for remote access)
MCP_TRANSPORT=streamable-http python server.py
# Point to local Next.js dev server
INDEX_URL=http://localhost:3000/content-index.json python server.py
Claude Desktop Configuration
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"arcology": {
"command": "python",
"args": ["C:/Users/blues/Claude Code Projects/arcology-node/mcp/server.py"],
"env": {
"INDEX_URL": "https://lifewithai.ai/content-index.json"
}
}
}
}
Deploy to Fly.io
cd mcp/
fly auth login
fly launch --name arcology-mcp --region dfw
fly deploy
Then point DNS: mcp.lifewithai.ai → Fly.io app.
Architecture
content-index.json (Netlify) → [HTTP fetch, cached 5 min] → MCP server (Fly.io) → agents via Streamable HTTP (/mcp)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.