Critical Raw Minerals & Urban Mining Oracle (x402)

Critical Raw Minerals & Urban Mining Oracle (x402)

Deterministic Web3 x402 Critical Minerals & Urban Mining Scrap Valuation Oracle for Autonomous AI Agents on Base (USDC)

Category
Visit Server

README

Critical Raw Minerals & Urban Mining Oracle (minerals-oracle-x402)

Glama.ai Cloud Run Base Network FastAPI Agent Protocol MCP

High-performance deterministic micro-oracle service designed for autonomous trading, supply chain, and RWA (Real World Asset) agents on Base Network. Serves real-time spot pricing, COMEX/LME cross-exchange arbitrage spreads, and urban-mining scrap benchmark yield valuations for critical raw physical commodities.


โšก Key Features

  1. Normalized Critical Commodities Price Feeds:

    • Silver (Ag): LBMA & COMEX spot in USD/troy_oz, USD/g, USD/kg.
    • Platinum (Pt): LPPM & NYMEX spot in USD/troy_oz, USD/g.
    • Copper (Cu): LME Grade A Cathode & COMEX in USD/mt, USD/lb, USD/kg.
    • Lithium (Li): Battery Grade 99.5% $\text{Li}_2\text{CO}_3$ / $\text{LiOH}$ in USD/mt, USD/kg.
    • Rare Earths (NdDy): Permanent magnet grade Neodymium-Dysprosium ($\text{PrNd}/\text{DyFe}$) composite in USD/kg.
  2. Locational Arbitrage & Basis Spreads:

    • COMEX vs. LME Copper arbitrage calculation factoring in trans-oceanic freight & import tariffs.
    • COMEX vs. LBMA Loco London Silver spread.
    • SMM Domestic China vs. Fastmarkets CIF Rotterdam Lithium premium/discount.
    • NYMEX vs. LPPM Platinum spread.
  3. Urban Mining & Circular Economy Valuation Engine:

    • EV_BATTERY_BLACK_MASS: Hydrometallurgical recovery of $\text{Li}$, $\text{Ni}$, $\text{Co}$, and $\text{Mn}$ with payable recovery yields and treatment charges (TC/RC).
    • AUTO_CATALYST_CERAMIC: Spent catalytic converter PGM recovery ($\text{Pt}$, $\text{Pd}$, $\text{Rh}$) from ceramic monolith assays.
    • E_WASTE_HIGH_GRADE_PCB: Precious and base metal extraction ($\text{Au}$, $\text{Ag}$, $\text{Cu}$) from shredded PCB feedstock.
    • WIND_EV_PERMANENT_MAGNETS: NdFeB scrap recycling for separated rare earth oxides ($\text{Nd}$, $\text{Dy}$, $\text{Pr}$).
  4. Web3 Monetization via x402 on Base:

    • Enforces micro-payments (0.005 USDC per query) via HTTP 402 challenge-response on Base (Chain ID 8453).
    • Native Base USDC token: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913.
    • Supports EIP-712/EIP-191 cryptographic signatures and facilitator verification.
  5. Multi-Agent Standards Native:

    • Google AP2 (/.well-known/ap2): Agent Protocol v2 manifest.
    • Model Context Protocol (MCP): Tool schema definitions (mcp_tool_spec.json) and /mcp/invoke dispatcher.
    • OpenAPI / Swagger (/docs): Standard machine-readable and interactive API documentation.

๐Ÿ“ Repository Structure

minerals-oracle-x402/
โ”œโ”€โ”€ app/
โ”‚   โ”œโ”€โ”€ __init__.py
โ”‚   โ”œโ”€โ”€ main.py              # FastAPI application, routing & MCP endpoints
โ”‚   โ”œโ”€โ”€ feed_engine.py       # Deterministic commodity pricing, spread & scrap engine
โ”‚   โ”œโ”€โ”€ x402_verifier.py     # HTTP 402 challenge & EIP-712 payment verifier
โ”‚   โ””โ”€โ”€ schemas.py           # Pydantic data contracts & schemas
โ”œโ”€โ”€ tests/
โ”‚   โ”œโ”€โ”€ __init__.py
โ”‚   โ””โ”€โ”€ test_client.py       # Autonomous agent payment test suite
โ”œโ”€โ”€ .well-known/
โ”‚   โ””โ”€โ”€ ap2.json             # Google Agent Protocol AP2 manifest
โ”œโ”€โ”€ mcp_tool_spec.json       # FastMCP tool definition for LLM agents
โ”œโ”€โ”€ Dockerfile               # Ultra-lightweight multi-stage container
โ”œโ”€โ”€ requirements.txt         # Python dependencies
โ””โ”€โ”€ README.md                # Documentation & quickstart

๐Ÿš€ Quick Start

1. Local Setup

# Clone and enter directory
cd minerals-oracle-x402

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run development server
uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload

Interactive documentation will be available at http://localhost:8000/docs.

2. Running via Docker

# Build lightweight container
docker build -t minerals-oracle-x402 .

# Run container
docker run -p 8000:8000 minerals-oracle-x402

๐Ÿ’ณ x402 Payment Flow Specification

sequenceDiagram
    autonumber
    actor Agent as Autonomous AI Agent
    participant Oracle as minerals-oracle-x402
    participant Base as Base Network (USDC)

    Agent->>Oracle: GET /api/v1/oracle/prices
    Oracle-->>Agent: HTTP 402 Payment Required<br/>(Nonce, Price: 0.005 USDC, Base Chain ID: 8453)
    Note over Agent: Agent signs payment challenge<br/>using private key (EIP-712/EIP-191)
    Agent->>Oracle: GET /api/v1/oracle/prices<br/>Header: Authorization: x402 <base64_payload>
    Oracle->>Oracle: Verify signature / Facilitator settle
    Oracle-->>Agent: HTTP 200 OK<br/>Certified Oracle Feeds & Attestation Hashes

Payment Authorization Header Format

Authorization: x402 eyJub25jZSI6ICIxYTIz...IiwgInNpZ25hdHVyZSI6ICIweDk5...In0=

Where the decoded JSON payload contains:

{
  "nonce": "7f8b92c4a90184b2ef019a823b102938",
  "signature": "0x...",
  "signer": "0xYourAgentWalletAddress"
}

๐Ÿค– MCP (Model Context Protocol) Integration

To use with Claude Desktop, Cursor, Gemini or Antigravity agents, load mcp_tool_spec.json.

Available tools:

  1. get_mineral_prices: Retrieve all current spot prices and unit conversions.
  2. get_arbitrage_spreads: Fetch COMEX/LME/SMM basis spreads and margins.
  3. calculate_urban_mining_value: Calculate batch recovery yields for EV Black Mass, Auto Catalysts, E-Waste, or Permanent Magnets.

Example Python Agent MCP tool call:

import httpx

resp = httpx.post(
    "http://localhost:8000/mcp/invoke",
    json={
        "name": "calculate_urban_mining_value",
        "arguments": {
            "scrap_category": "EV_BATTERY_BLACK_MASS",
            "quantity_metric_tons": 5.0,
            "custom_assay_overrides": {"Li": 4.1, "Co": 6.5}
        }
    },
    headers={"X-Dev-Bypass": "true"}  # Or with valid x402 signature
)
print(resp.json())

๐Ÿงช Running Tests

Execute the automated test suite verifying 402 challenge flow, EIP-712 cryptographic verification, scrap calculations, and AP2 endpoints:

pytest -v tests/test_client.py

๐Ÿ“œ License

MIT License. Built for Autonomous Agent Commerce and Critical Mineral Resilience.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured