> For the complete documentation index, see [llms.txt](https://docs.chaingpt.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/summary.md).
# Summary
## ChainGPT Developer Kit for Claude Code
The ChainGPT Developer Kit is a Claude Code plugin that transforms your AI assistant into a Web3 engineering co-pilot. It provides a complete API reference, 12 MCP tools for direct API access, 45+ audited Solidity patterns, 10 project templates, and a zero-credit mock server for testing, all accessible from your Claude Code environment with no context-switching.
### What is it?
Building with Web3 AI APIs typically means constant switching between documentation, SDKs, and Stack Overflow. You paste an endpoint, get the parameters wrong, burn API credits debugging, and repeat. This plugin eliminates that friction by embedding the entire ChainGPT platform directly into Claude Code.
Once installed, Claude already knows every ChainGPT endpoint, parameter, credit cost, and best practice. You describe what you want built, and Claude generates production-ready code — or calls the APIs directly via MCP tools.
### Who is it for?
The plugin serves two audiences:
**Developers** who want to integrate ChainGPT APIs into blockchain applications. Whether you're building a Web3 chatbot, an NFT marketplace, a smart contract auditing pipeline, or a crypto news dashboard, the plugin provides the exact SDK snippets, REST examples, and project scaffolds you need.
**Teams and product builders** evaluating Web3 AI infrastructure. The plugin includes a product selection guide, cost estimation tools, and multi-product composition patterns that help you architect complete solutions before writing a line of code.
### Key Numbers
| Metric | Value |
| ----------------- | ------------------------------------------------------------------------ |
| Products covered | 7 (LLM, NFT, Contract Generator, Auditor, News, AgenticOS, Solidity LLM) |
| MCP tools | 12 direct API access tools |
| Project templates | 10 production-ready scaffolds |
| Solidity patterns | 45+ audited, gas-optimized contracts |
| Test coverage | 79 passing tests (53 MCP + 26 mock server) |
| Reference docs | 16 detailed API/SDK documentation files |
| Code examples | 8 working examples (JavaScript + Python) |
### How it works
The plugin operates at three levels:
**Knowledge layer** — Claude has access to 16 comprehensive reference documents covering every endpoint, parameter, response format, error code, and SDK method across all 7 products. When you ask Claude to build something, it generates correct code on the first try.
**Execution layer** — The MCP server gives Claude 12 tools to call ChainGPT APIs directly from the conversation. Generate images, mint NFTs, audit contracts, fetch news — all without leaving the chat.
**Scaffolding layer** — 10 project templates and 45+ Solidity patterns let Claude compose production-ready applications from proven, audited building blocks instead of generating everything from scratch.
### Quick example
You: "Generate an NFT of a cyberpunk samurai and mint it on Polygon"
Claude: I'll use the ChainGPT NFT Generator to create your image and mint it on-chain.
1. Generating image with VisionaryForge model... done
2. Queuing for on-chain minting on Polygon (chainId: 137)... done
3. Polling for completion... done
* NFT minted successfully!
* Collection ID: cgpt-a8f3...
* Token URI: ipfs\://QmX7k...
* Cost: 2 credits ($0.02)
### Links
| Resource | URL |
| ------------------- | ------------------------------------------------------------------------------------------------------ |
| GitHub repository | [github.com/ChainGPT-org/chaingpt-claude-skill](https://github.com/ChainGPT-org/chaingpt-claude-skill) |
| Developer docs | [docs.chaingpt.org](https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk) |
| API dashboard | [app.chaingpt.org/apidashboard](https://app.chaingpt.org/apidashboard) |
| Purchase credits | [app.chaingpt.org/addcredits](https://app.chaingpt.org/addcredits) |
| Web3 AI Grant ($1M) | [chaingpt.org/web3-ai-grant](https://www.chaingpt.org/web3-ai-grant) |
| ChainGPT website | [chaingpt.org](https://www.chaingpt.org) |
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/summary.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.