> ## Documentation Index
> Fetch the complete documentation index at: https://docs.meteora.ag/llms.txt
> Use this file to discover all available pages before exploring further.
# Agents
> Use AI agents with Meteora docs, APIs, SDKs, and launch tooling.
Meteora is built to be legible to AI agents: docs are available as MCP tools, static LLM indexes, raw Markdown, SDK guides, API references, and command-driven launch workflows. Use the docs layer for context, then execute through your own code, wallet, SDK integration, or Meteora Invent when an action is intentional.
## Agent Workflow
1. **Discover** the relevant product, guide, SDK, or API page with [llms.txt](/agents/llms-txt) or [Documentation MCP](/agents/mcp).
2. **Read exact context** from raw Markdown pages or MCP page retrieval before writing code.
3. **Implement** against Meteora SDKs, REST API references, and program docs.
4. **Execute deliberately** through scripts, wallets, SDK transactions, or [Meteora Invent](/invent/actions), with signing controlled by the user.
Meteora's documentation MCP is read-only. It helps agents understand Meteora; it does not sign transactions, manage private keys, execute swaps, create pools, or edit this documentation.
## Pick the Right Entry Point
Use Documentation MCP when the agent supports MCP and should search or read current docs in context.
Use `llms.txt` when you need static, crawlable documentation context.
Use a raw Markdown export when you already know the page URL and want clean Markdown.
Use Developer Guides when you need SDK setup, account models, instructions, events, errors, and examples.
Use API Reference pages when you need endpoint schemas, parameters, response fields, and rate-limit context.
Use Meteora Invent when you need config-driven commands for pools, launches, or protocol actions.
## Agent Surfaces
For agents that need to discover, reason, implement, or prepare actions with Meteora:
Search and read Meteora docs from Claude, Claude Code, Cursor, VS Code, Windsurf, ChatGPT, and other MCP-compatible tools.
Static LLM-optimized indexes and raw Markdown exports for agents, crawlers, and custom retrieval pipelines.
SDKs, program references, API references, and examples for building Meteora integrations.
Config-driven commands for launching pools and running supported onchain workflows with user-controlled signing.
## Local and Hosted Agents
For Claude Code, Cursor, Codex, VS Code, and Windsurf, connect Documentation MCP, read raw Markdown when needed, install SDKs locally, run tests, and execute scripts only with explicit wallet and network configuration.
For Claude.ai, ChatGPT, and other MCP clients, connect Documentation MCP for current docs context, use `llms.txt` links for fallback retrieval, and keep wallet signing or production execution outside the chat unless a trusted execution tool is explicitly configured.
## Safe Agentic Usage
* Ask the agent to cite the Meteora docs pages it used before implementing.
* Never paste seed phrases, private keys, or production wallet secrets into an agent chat.
* Use localnet or devnet before mainnet when testing generated scripts.
* Keep transaction review and signing under user control.
* Treat large automated changes or onchain actions as proposals until reviewed.
## Prompt Starters
```text theme={"system"}
Use the Meteora Docs MCP to find the current DAMM v2 TypeScript SDK guide, then draft the smallest safe integration plan for adding liquidity.
```
```text theme={"system"}
Start from Meteora llms.txt, identify the DBC pages needed for migration handling, then fetch only those Markdown pages before writing code.
```