# llms.txt Source: https://docs.meteora.ag/agents/llms-txt Static documentation indexes and raw Markdown endpoints for LLMs and AI agents. Meteora provides structured documentation files purpose-built for LLMs and AI agents, following the [llmstxt.org](https://llmstxt.org) standard. Use `llms.txt` when your agent needs a compact map of the docs. Use [Documentation MCP](/agents/mcp) when your AI tool can call MCP tools and should search or read pages interactively. ## llms.txt A plain Markdown file containing a structured index of Meteora documentation with titles and descriptions for each indexed page: * **Site title** as an H1 heading * **Sections** for major areas such as Get Started, User Guides, Core Products, Helper Products, Developer Guides, Invent, Agents, Protocol, and Resources * **Links with descriptions** for product guides, SDK references, API references, and resources * **OpenAPI spec links** where API reference specifications are indexed Open the llms.txt for Meteora docs ```mdx theme={"system"} # Meteora Documentation ## Get Started - [We Build Liquidity Pools](https://docs.meteora.ag/get-started.md): The Most Composable Liquidity Layer... - [What is DLMM?](https://docs.meteora.ag/core-products/dlmm/what-is-dlmm.md): Learn how Meteora's DLMM organizes liquidity... - [DAMM v2 Developer Guide](https://docs.meteora.ag/developer-guides/damm-v2/index.md): Learn how to build DAMM v2 integrations... - [Dynamic Bonding Curve Developer Guide](https://docs.meteora.ag/developer-guides/dbc/index.md): Learn how to build Dynamic Bonding Curve integrations... ## OpenAPI Specs - [openapi](https://docs.meteora.ag/api-reference/dlmm/openapi.json) ``` This is the best first fetch for agents that need to decide which Meteora product, guide, SDK reference, API reference, or raw Markdown page to read next. ## llms-full.txt Open the llms-full.txt for Meteora docs While `llms.txt` provides a concise index, `llms-full.txt` contains the **entire documentation site** as context, including descriptions, code examples, guides, API references, and product explanations. Use `llms-full.txt` when: * Your AI tool needs **complete, granular context** for deep indexing * You're building **custom RAG pipelines** over Meteora docs * You want **every code example** available for reference ## Raw Markdown Pages Any documentation page can be accessed as raw Markdown, making it easy for AI agents to consume individual pages programmatically. **Method 1: Append `.md` to the URL** ```bash theme={"system"} curl https://docs.meteora.ag/core-products/dlmm/what-is-dlmm.md curl https://docs.meteora.ag/core-products/damm-v2/what-is-damm-v2.md curl https://docs.meteora.ag/core-products/dbc/what-is-dbc.md curl https://docs.meteora.ag/developer-guides/dlmm/typescript-sdk/getting-started.md curl https://docs.meteora.ag/developer-guides/damm-v2/typescript-sdk/getting-started.md curl https://docs.meteora.ag/developer-guides/dbc/typescript-sdk/getting-started.md ``` **Method 2: Use the `Accept` header** ```bash theme={"system"} curl -H "Accept: text/markdown" https://docs.meteora.ag/developer-guides/damm-v2/typescript-sdk/getting-started ``` Both methods return the page content as `text/markdown`. ## How Agents Should Use These Files | Need | Best entrypoint | | :--------------------------------- | :-------------------------------------- | | Discover the docs structure | `https://docs.meteora.ag/llms.txt` | | Ingest the full docs corpus | `https://docs.meteora.ag/llms-full.txt` | | Read one exact page | Append `.md` to the page URL | | Search and read from an MCP client | `https://docs.meteora.ag/mcp` | For most agent workflows, start with `llms.txt`, fetch only the relevant `.md` pages, and use `llms-full.txt` only when you intentionally want the full corpus in one document. # Documentation MCP Source: https://docs.meteora.ag/agents/mcp Connect AI tools to Meteora docs through Mintlify's hosted Model Context Protocol server. Meteora's documentation MCP is the live, tool-call version of these docs for AI agents. It is hosted by Mintlify at `https://docs.meteora.ag/mcp` and follows Mintlify's documentation MCP model: agents can search indexed documentation, then read exact page content from a read-only docs filesystem. ## What is MCP? MCP is an open protocol that connects AI assistants to external data sources and tools. With Meteora's documentation MCP server, your AI tool can: * **Search documentation**: find relevant product docs, developer guides, SDK references, and API references * **Read exact pages**: retrieve full MDX/Markdown content through Mintlify's virtual docs filesystem * **Inspect API reference content**: look up indexed endpoint docs, request/response schemas, parameters, and errors where available * **Use docs without web-search noise**: answer from the current indexed Meteora documentation instead of generic search results This is a read-only documentation server. It does not execute API calls, submit transactions, sign with a wallet, mutate documentation, or manage funds. ## Endpoint Meteora's public documentation MCP server is available at: ``` https://docs.meteora.ag/mcp ``` Connect an MCP-compatible AI tool to Meteora documentation This endpoint uses HTTP transport and exposes Meteora's indexed documentation through MCP. ## Documentation MCP vs Mintlify MCP Mintlify offers two related MCP experiences: | Server | Audience | What it can do | | :----------------------------------------------------- | :-------------------------- | :----------------------------------------------------------------------------------- | | **Documentation MCP** at `https://docs.meteora.ag/mcp` | Meteora builders and users | Search and read Meteora's published docs | | **Mintlify MCP** at `https://mcp.mintlify.com` | Trusted documentation teams | Edit Mintlify content, update navigation, modify `docs.json`, and open pull requests | Use Meteora's documentation MCP when an agent needs current Meteora context. Use Mintlify's authenticated MCP only if you are part of the docs team and want an agent to make documentation changes through Mintlify's branch and pull request workflow. ## What You Get Once connected, your AI assistant can search and read: | Resource | Description | | :---------------------- | :-------------------------------------------------------------------------------- | | **Documentation pages** | Product explanations, user guides, developer guides, and reference docs | | **API references** | Indexed endpoint docs and OpenAPI-backed request/response details where available | | **Program references** | Account, instruction, event, and error documentation for Meteora programs | | **Skill resources** | `skill.md` resources, when available through the docs site | Combine MCP with [llms.txt](/agents/llms-txt): use MCP for in-editor queries and use `llms.txt`, `llms-full.txt`, or raw Markdown exports for batch processing and RAG pipelines. ## Setup **How to enable Meteora Docs MCP in Claude Code:** 1. Open your terminal. 2. Add Meteora's MCP server by running: ```bash theme={"system"} claude mcp add --transport http meteora https://docs.meteora.ag/mcp ``` 3. Launch Claude Code and start chatting with Meteora. **Or add to your project’s `.mcp.json`:** ```json theme={"system"} { "mcpServers": { "meteora": { "url": "https://docs.meteora.ag/mcp" } } } ``` **Verify with:** ```bash theme={"system"} claude mcp list ``` **Setup Meteora Docs MCP in Claude:** 1. Go to [**Connectors**](https://claude.ai/settings/connectors) in your Claude settings. 2. Select **Add custom connector**. 3. Set the name to **Meteora** and the URL to **[https://docs.meteora.ag/mcp](https://docs.meteora.ag/mcp)**. 4. When chatting, click the attachments button (plus icon) and select the Meteora connector. **Setup Meteora Docs MCP in Cursor:** 1. Open the command palette with `Cmd + Shift + P` (or `Ctrl + Shift + P` on Windows). 2. Search for **Open MCP settings**. 3. Add the following to your `mcp.json` file: ```json theme={"system"} { "mcpServers": { "meteora": { "url": "https://docs.meteora.ag/mcp" } } } ``` 4. Save and reload Cursor. **Setup Meteora Docs MCP in VS Code:** 1. Create or open `.vscode/mcp.json`. 2. Add the following server configuration: ```json theme={"system"} { "servers": { "meteora": { "type": "http", "url": "https://docs.meteora.ag/mcp" } } } ``` 3. Save the file and reload your MCP-enabled VS Code environment. **Using Meteora Docs MCP in Windsurf:** 1. Open the command palette with `Cmd + Shift + P` (or `Ctrl + Shift + P` on Windows). 2. Search for **Windsurf: Configure MCP Servers**. 3. Add the following to your `mcp_config.json` file: ```json theme={"system"} { "mcpServers": { "meteora": { "serverUrl": "https://docs.meteora.ag/mcp" } } } ``` 4. Save and restart Windsurf. ### Other MCP-Compatible Tools Any tool that supports HTTP MCP servers can connect to `https://docs.meteora.ag/mcp`. ## Example Prompts ```text theme={"system"} Use the Meteora Docs MCP to find the current DLMM TypeScript SDK swap flow, then summarize the files I should read before implementing it. ``` ```text theme={"system"} Search Meteora docs for DAMM v2 fee scheduler and rate limiter behavior. Cite the relevant docs pages before suggesting configuration values. ``` ```text theme={"system"} Read the DBC migration docs and program error reference, then help me design a defensive integration checklist. ``` For onchain execution, keep signing and transaction submission in your own scripts, wallet, SDK integration, or [Meteora Invent](/invent/actions). The documentation MCP supplies context; it does not perform the action. # Agents Source: https://docs.meteora.ag/agents/overview Use AI agents with Meteora docs, APIs, SDKs, and launch tooling.