Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

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)

# 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

Last updated