> ## Documentation Index > Fetch the complete documentation index at: https://docs.usenash.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Nash exposes two MCP servers. The docs MCP server at https://docs.usenash.com/mcp searches this documentation and needs no credentials. The Nash MCP server at https://mcp.usenash.com/mcp operates an organization's deliveries and needs a Nash API key. See https://docs.usenash.com/reference/build-with-ai. > Use the Sandbox environment (https://api.sandbox.usenash.com/v1) for anything that creates or dispatches deliveries during development. # Build with AI > Every way to put an AI assistant or agent to work on your Nash integration — the docs MCP server, machine-readable references, and the Nash MCP server. Nash is built to be worked with through AI as much as through code. Whether you're using a coding assistant to write the integration, or building an agent that runs deliveries once it's live, there's a first-class way in — and it's the same open standard, the [Model Context Protocol](https://modelcontextprotocol.io) (MCP), on both ends. ## Two MCP servers Nash exposes two MCP servers, and they do different jobs. | | **Docs MCP server** | **Nash MCP server** | | :-------------- | :------------------------------------------ | :---------------------------------------------------------- | | What it reaches | This documentation | Your organization's deliveries, couriers, and configuration | | Who it's for | Anyone building or debugging an integration | Agents that operate deliveries on your behalf | | Credentials | None | Your Nash API key | | Access | Open to everyone | Enabled per organization | | URL | `https://docs.usenash.com/mcp` | `https://mcp.usenash.com/mcp` | The [docs MCP server](/reference/docs-mcp-server) is the one to connect while you build. It lets Claude, Cursor, VS Code, or any MCP client search and read the current docs, so the assistant writing your `POST /orders` call is reading the same request schema you are. The [Nash MCP server](/reference/mcp-integration) is the one to connect when an agent should *act*: create a delivery when an order lands, answer "where's my order?" with live status, request a refund in the same conversation. It runs with your API key's permissions and is enabled for your organization by our team. A coding agent doing a Nash integration benefits from both — the docs for how the platform works, the Nash server for trying calls against your sandbox as it goes. ## Machine-readable references Not every assistant can connect to an MCP server. For the ones that take pasted context, links, or fetched URLs, the whole documentation is published in formats built for models: | Resource | URL | | :----------------------------------------- | :----------------------------------------------------------------------------------------------------------- | | Condensed index of every page | [`/llms.txt`](https://docs.usenash.com/llms.txt) | | The full documentation in one file | [`/llms-full.txt`](https://docs.usenash.com/llms-full.txt) | | Any single page as Markdown | Append `.md` to its URL, or request it with `Accept: text/markdown` | | The public OpenAPI specification | [`/api-reference/openapi.json`](https://docs.usenash.com/api-reference/openapi.json) | | What an agent can do with Nash, as a skill | [`/skill.md`](https://docs.usenash.com/skill.md) — install it with `npx skills add https://docs.usenash.com` | The menu at the top of every page offers the same things one page at a time: copy it as Markdown, open it in Claude, or connect the docs MCP server to Cursor or VS Code. [Using LLMs with the Nash API](/api-reference/using-llms-with-nash-api) covers how to prompt with these, and what to keep out of the prompt. ## An agent that's already wired in If what you want is an operations agent that knows Nash, and you'd rather not build one, [Nash Agent](/nash-agent/overview) ships with the platform. It has the same tools the Nash MCP server exposes, runs inside the Portal, and can be reached over [chat channels](/nash-agent/channels) or [embedded](/nash-agent/embedded-chat) in your own product. ## Where to start Connect your assistant to the docs. No credentials, one URL. Give an agent the tools to run deliveries with your API key. The operations copilot that needs no integration at all.