Thirdweb AI

What is Thirdweb AI about?

Thirdweb AI offers a unified framework that bridges on‑chain data with generative AI, enabling developers to query blockchain information, manage wallets, interact with smart contracts, store files on IPFS, and execute blockchain tasks via natural language instructions.

How to use Thirdweb AI?

1. Install the MCP server (Python) and set the THIRDWEB_SECRET_KEY environment variable.
2. Install the SDK:

   pip install "thirdweb-ai[all]"   # full install
   # or install specific adapters, e.g.
   pip install "thirdweb-ai[openai]"
   

3. Initialize services in code:

   from thirdweb_ai import Insight, Engine, EngineCloud, Nebula, Storage
   insight = Insight(secret_key=...)
   engine = Engine(...)
   engine_cloud = EngineCloud(secret_key=..., vault_access_token=...)
   storage = Storage(secret_key=...)
   nebula = Nebula(secret_key=...)
   

4. Create tools for an AI agent (Nebula alone is recommended) and integrate with a framework such as LangChain or OpenAI Agents.
5. Run the agent to perform blockchain tasks based on natural‑language prompts.

Key Features of Thirdweb AI

• Insight: Multi‑chain data intelligence (chains, transactions, blocks, events, prices, tokens).
• Engine: Secure wallet management, read‑only contract queries, write operations and transaction signing.
• EngineCloud: Server‑side wallet handling with KMS, contract interaction, transaction history, balance queries.
• Storage: Decentralized upload/fetch to IPFS via the thirdweb gateway.
• Nebula: Natural‑language AI agent that internally orchestrates the other services, exposing a single toolset.
• Framework adapters: Ready‑to‑use integrations for OpenAI, LangChain, Coinbase Agentkit, GOAT SDK, and many more.
• Publish workflow: Automated CI/CD pipeline for PyPI releases.

Use Cases of Thirdweb AI

• Building AI assistants that can answer blockchain‑related questions (e.g., token price, transaction status).
• Automating wallet actions such as sending funds or signing messages through conversational interfaces.
• Enabling developers to query smart‑contract events and logs without writing low‑level code.
• Storing and retrieving NFTs or other assets on IPFS directly from AI‑driven workflows.
• Integrating blockchain capabilities into existing LLM applications (ChatGPT plugins, custom agents, etc.).

FAQ

Q: Do I need to import all services when using Nebula? A: No. Nebula internally uses Insight, Engine, EngineCloud, and Storage, so importing those separately can cause conflicts.

Q: Which environments are supported for the MCP server? A: The server runs as a Python package (thirdweb-mcp). Install via uvx or pipx and provide THIRDWEB_SECRET_KEY.

Q: How can I add support for a new LLM framework? A: Implement an adapter following the pattern in thirdweb_ai/adapters/ and expose get_<framework>_tools.

Q: Is there a TypeScript SDK? A: It is planned for the future; currently only the Python SDK is available.

Q: How are security vulnerabilities reported? A: Email security@thirdweb.com directly; do not use the public issue tracker.

thirdweb AI

AI Agents with Onchain Intelligence

📖 Overview

thirdweb AI is thirdweb's comprehensive toolkit for blockchain data analysis, wallet management, and AI agent interaction with blockchains. It simplifies complex blockchain operations into five core components: Insight for data analysis, Engine for wallet and contract operations, EngineCloud for cloud-based engine operations, Storage for decentralized file management, and Nebula for natural language-powered blockchain interactions.

🌐 Features

Insight

Comprehensive blockchain data intelligence:

• Chains: Multi-chain support and network information
• Transactions: Transaction analysis and monitoring
• Blocks: Block data exploration and metrics
• Events: Smart contract event tracking and filtering
• Prices: Real-time token price feeds
• Tokens: Detailed token information and analytics

Engine

Core blockchain interaction capabilities:

• Wallet: Secure wallet management and transaction signing
• Read: Read operations for smart contracts and blockchain data
• Write: Transaction creation and contract interaction

EngineCloud

Cloud-based engine operations with advanced capabilities:

• Server Wallets: Create and manage server wallets with KMS integration
• Contract Interaction: Read from and write to smart contracts
• Transaction Management: Send transactions and query transaction history
• Balance Queries: Check native token balances on various chains

Storage

Decentralized storage capabilities:

• Upload: Upload files, directories, and JSON data to IPFS
• Fetch: Retrieve content from IPFS using thirdweb gateway

Nebula

AI agent blockchain interaction:

• Natural Language Agent Action: Completing blockchain tasks through natural language instructions

🚀 Quickstart

MCP Server

Installation

### Run using uvx
THIRDWEB_SECRET_KEY=... \
    uvx thirdweb-mcp

### Install and run using pipx (and run thirdweb-mcp)
pipx install thirdweb-mcp

THIRDWEB_SECRET_KEY=... \
    thirdweb-mcp

More information

Python SDK

Installation

# Install core package with all framework adapters
pip install "thirdweb-ai[all]"

# Or install with specific framework adapters
pip install "thirdweb-ai[openai]"    # For OpenAI Agents
pip install "thirdweb-ai[langchain]" # For LangChain
pip install "thirdweb-ai[agentkit]" # For Coinbase Agentkit
pip install "thirdweb-ai[goat]" # For GOAT SDK
# ... many more framework supported

See the list of supported framework and installation guides

Basic Usage

from thirdweb_ai import Engine, EngineCloud, Insight, Nebula, Storage, Tool

# Initialize services
insight = Insight(secret_key=...)
nebula = Nebula(secret_key=...)
engine = Engine(...)
engine_cloud = EngineCloud(secret_key=..., vault_access_token=...)  # For cloud-based operations
storage = Storage(secret_key=...)

# Example: Create tools for AI agents
# Option 1: Use Nebula alone (recommended when you need a self-sufficient blockchain agent)
# Nebula already uses most other services internally
tools = [
    *nebula.get_tools(),
]

# Option 2: Use individual services directly without Nebula
# tools = [
#     *insight.get_tools(),
#     *engine.get_tools(),
#     *engine_cloud.get_tools(),
#     *storage.get_tools(),
# ]

# Example: Framework integration (LangChain)
from thirdweb_ai.adapters.langchain import get_langchain_tools
langchain_tools = get_langchain_tools(tools)
agent = create_tool_calling_agent(tools=langchain_tools, ...)

# Example: Framework integration (OpenAI Agents)
from thirdweb_ai.adapters.openai import get_openai_tools
openai_tools = get_openai_tools(tools)
agent = Agent(name="thirdweb Assistant", tools=tools)

# see python/examples for other framework integration

More information

TypeScript SDK

Coming soon.

📜 Documentation

For comprehensive documentation, please visit:

• thirdweb Documentation

🚨 Security and Bug Reports

We take security seriously. If you discover a security vulnerability within thirdweb AI, please email security@thirdweb.com rather than using the issue tracker.

For non-security-related bugs, please use the GitHub issue tracker.

⚠️ Important Usage Notes

When using Nebula, do not combine it with other tools (Insight, Engine, EngineCloud, Storage) in the same agent implementation as Nebula already calls these tools in the background. Using them together can lead to compatibility issues and unexpected behavior.

📦 Publishing Workflow

To publish a new version of thirdweb AI packages:

1. Create a git tag for the new version: git tag -a v0.X.Y -m "Release v0.X.Y"
2. Push the tag to GitHub: git push origin v0.X.Y
3. Go to GitHub and create a release using this tag
4. The CI/CD pipeline will automatically build and publish both packages to PyPI with matching version numbers

📧 Contact

• Website: thirdweb.com
• X: @thirdweb
• Telegram: Join our community
• Discord: Join our community
• Email: support@thirdweb.com

📝 License

thirdweb AI is licensed under the Apache-2.0 License. See the LICENSE file for details.