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

# Overview

## AI

Panora is built to be consumed by AI agents as much as by humans. This section indexes every surface designed for coding agents (Claude Code, Cursor, Codex, ChatGPT, Gemini) and AI-augmented developer tools.

### What's available

| Surface          | Use it for                                                                                  | Get started                                                                     |
| ---------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| **MCP Servers**  | Letting an AI assistant read these docs *and* execute swaps / DCA / limit orders            | Docs MCP at `docs.panora.exchange/~gitbook/mcp`; executor MCP via `@panora/cli` |
| **Agent Skills** | Drop-in playbooks that teach Claude Code / Cursor / Codex how to integrate Panora correctly | `npx skills add panora-exchange/agent-skills`                                   |
| **llms.txt**     | Pointing ChatGPT / Claude.ai / Gemini at the entire doc set in one fetch                    | `docs.panora.exchange/llms.txt`                                                 |
| **CLI**          | LLM-friendly command line for swap, DCA, limit, and 15+ other commands                      | `npm install -g @panora/cli`                                                    |

### Which one do I need?

| You're...                                            | Start with                                                                                                          |
| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| Building a dApp or bot programmatically              | Agent Skills — gives your AI assistant Panora-specific context (which SDK, exact-match token rules, fee-payer flow) |
| Trading or scripting from the terminal               | CLI + wire its MCP server into Claude Code or Cursor                                                                |
| Asking ChatGPT / Claude.ai about Panora              | Drop them the llms.txt URL                                                                                          |
| Wanting your agent to read the live docs as it works | Add the Docs MCP endpoint                                                                                           |

### Quick start (Claude Code)

```bash
# 1. Install the CLI + executor MCP
npm install -g @panora/cli

# 2. Wire both MCP servers into Claude Code
claude mcp add --scope user --transport stdio \
  -- panora npx -y -p @panora/cli panora-mcp

claude mcp add --scope user --transport http \
  panora-docs https://docs.panora.exchange/~gitbook/mcp

# 3. Install the agent skills (auto-detects Claude Code / Cursor / Codex)
npx skills add panora-exchange/agent-skills

# 4. Verify
claude mcp list
```

Open Claude Code and ask *"Swap 1 APT to USDC on Panora"* — the agent discovers the skill, routes to the executor MCP, and submits on-chain.

### Resources

* 📦 [`@panora/cli`](https://www.npmjs.com/package/@panora/cli) on npm
* 📚 [`panora-exchange/agent-skills`](https://github.com/panora-exchange/agent-skills) on GitHub
* 🔌 [Live Docs MCP endpoint](https://docs.panora.exchange/~gitbook/mcp)
* 📄 [llms.txt](https://docs.panora.exchange/llms.txt) · [llms-full.txt](https://docs.panora.exchange/llms-full.txt)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.panora.exchange/ai/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.