🔮 TCG Oracle Tools

LangChain, CrewAI & OpenAI-compatible tools for trading card game intelligence.

Drop TCG search and daily market snapshots into any AI agent in under 60 seconds.

The packaged tools are tcg_search and tcg_market — both free, no key required. AI grading and conformal risk forecasts are paid endpoints on the same oracle and are called over HTTP (see the endpoint table below) or through the hosted MCP server at https://mcp.the-undesirables.com — they are not bundled as LangChain tools yet.

Install

pip install tcg-oracle-tools

With LangChain support:

pip install tcg-oracle-tools[langchain]

Quick Start (Standalone)

from tcg_oracle import TCGOracleClient

client = TCGOracleClient()

# Search 446K+ products
results = client.search("Charizard", limit=5)
for card in results.results:
    print(f"{card.name}: ${card.market_price}")

# Market snapshot
market = client.market("Pokemon")
print(f"Tracking {market.total_products} products")

LangChain Agent

from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI
from tcg_oracle.langchain import TCGSearchTool, TCGMarketTool

tools = [TCGSearchTool(), TCGMarketTool()]
agent = initialize_agent(tools, ChatOpenAI(), agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)
agent.run("What's the most expensive Pokemon card right now?")

OpenAI Function Calling

import openai
from tcg_oracle.openai_spec import tools, handle_tool_call

response = openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Find me Pikachu cards under $50"}],
    tools=tools(),
)

if response.choices[0].message.tool_calls:
    result = handle_tool_call(response.choices[0].message.tool_calls[0])
    print(result)

CrewAI

from crewai_tools import tool
from tcg_oracle import TCGOracleClient

client = TCGOracleClient()

@tool("Search TCG Products")
def search_tcg(query: str) -> str:
    """Search trading card products by name and get market prices."""
    result = client.search(query)
    return str([{"name": c.name, "price": c.market_price} for c in result.results])

AutoGPT Plugin

Point AutoGPT at the OpenAPI spec:

https://oracle.the-undesirables.com/openapi.json

API Endpoints

Agent-to-Agent (Virtuals ACP v2)

TCG Oracle is registered on Virtuals ACP. Autonomous agents can discover, hire, and pay for services using USDC on Base.

📝 License & Commercial Use

This project is licensed under the Business Source License 1.1 (BUSL-1.1).

We build in public and support the developer ecosystem — but we also protect the infrastructure and IP of The Undesirables LLC.

✅ What You CAN Do (Free)

• Personal & Educational Use — Download, modify, and run locally for learning, research, or personal projects.
• Non-Competing Applications — Integrate our packages into your app, provided your app does not offer TCG market intelligence, pricing aggregation, AI card grading, or on-chain price oracle services as its primary function.
• MCP / Agent Integration — Connect your AI agent to our tools for non-commercial use.
• Community Contributions — Security audits, bug fixes, and PRs are always welcome.

🚫 What You CANNOT Do (Use Limitation)

• Competing Service — You may not use this code to operate a competing TCG market intelligence, pricing aggregation, AI card grading, or on-chain price oracle service.
• Commercial Resale — You may not wrap our API, data pipelines, or AI models into a paid service without a commercial license.
• Hosted SaaS — You may not host this software as a service for third parties without written permission.

🔓 Open-Source Conversion

On June 1, 2030 (or 4 years after the first public release of each version), this code automatically converts to the MIT License — fully open source, forever.

🤝 Commercial Licensing

Building a commercial product? Want guaranteed API access or white-label integration? Contact us:

📧 theundesirables7@gmail.com · 🐦 @undesirables_ai

© 2026 The Undesirables LLC