> For the complete documentation index, see [llms.txt](https://docs.goassay.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.goassay.ai/developers/readme.md).

# Developer docs

Connect an AI client, protect a provider endpoint or understand Assay's payment and verification flow.

These docs are for people installing Assay in an AI client, connecting an API as a provider or building their own integration. Start with the path for your role; the setup pages include the required web actions.

## Use tools

[Install assay-mcp](/developers/use-tools-get-started/install-assay-mcp.md) to give your AI one connection to tools whose descriptions, prices and provider quality you can inspect before paying. Connect a local AI client and sign in through your browser. Use the published package **@goassay-ai/mcp**.

Continue through **How paying works** and **Spending limits** when you want paid calls. Your payment key stays on your computer; you approve its spending permission in your wallet. Hosted connectors (claude.ai, ChatGPT, and connectors added in Claude Desktop) make free calls only.

## List your API

Earn from your API by serving tools and backing paid tools with stake. Start with [API key or signature](/developers/list-your-api-get-started/api-key-or-signature.md) to choose how your endpoint authenticates Assay requests. That page leads to two alternatives: put the ready-made verifier in a Cloudflare Worker, or verify in your Node, Python or Go service.

The provider setup pages cover request authentication. **Under the hood** explains how Assay measures returned results, how those checks affect payment and what stake backs. Read the receipt's check results rather than treating a settled payment as proof of correctness.

## Under the hood

* [Architecture](/developers/under-the-hood/architecture.md) — the client, Assay, provider and payment contracts.
* [Life of a paid call](/developers/under-the-hood/life-of-a-call.md) — request, local signature, result and payment.
* [How calls are verified](/developers/under-the-hood/verification.md) — checks, decisions and their limits.
* [Settlement and the hold window](/developers/under-the-hood/settlement.md) — reservations, refunds, collection and owed calls.

Payments and stake use **USDG** on **Robinhood Chain**. The hosted MCP connection is `https://mcp.goassay.ai/`.

## Reference

* [Smart contracts](/developers/reference/smart-contracts.md) — escrow, stake, permissions and events.
* [MCP tools](/developers/reference/mcp-tools.md) — discovery, calling tools and result metadata.

## Go further

* Overview: [Welcome to Assay](https://docs.goassay.ai) for walkthroughs in the web app.

## Next

* [Install assay-mcp](/developers/use-tools-get-started/install-assay-mcp.md)


---

# 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.goassay.ai/developers/readme.md?ask=<question>&goal=<user_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.