# llms.txt - For AI Agents & Answer Engines

Swytchcode publishes a canonical [`/llms.txt`](/llms.txt) file at the root of this domain for AI agents, answer engines, and crawler tools.

It is a plain-text, machine-readable summary of Swytchcode's current developer experience, including:

- CLI installation and authentication workflows
- Managed Authentication and credential resolution
- Runtime tool execution pipeline and execution policies
- Retries, timeouts, and idempotency for safety
- Runtime SDKs for JavaScript and Python
- MCP server setup and API access for agents
- Open source runtime repos and integration docs

## Why llms.txt matters

AI systems increasingly answer directly from structured documentation instead of just ranking links. `/llms.txt` serves as an authoritative summary layer that tells agents:

- what Swytchcode does
- how to install and run the CLI
- how to connect authenticated providers
- how tools execute reliably through managed runtime behavior
- where the canonical docs and source code live

This helps AI assistants return accurate answers and routes them to the right docs for Swytchcode.

## What this page documents

This page collects the latest Swytchcode documentation topics relevant to AI agents and trusted tool execution.

- **[CLI Overview](/cli/overview/)** - Install the Swytchcode CLI, authenticate, and start executing tools.
- **[Authentication](/guides/authentication/)** - Learn how account and provider authentication works.
- **[Managed Authentication](/guides/managed-authentication/)** - Secure credential storage and provider credential resolution.
- **[Execution Pipeline](/guides/execution-pipeline/)** - The full runtime flow from tool resolution to API response.
- **[Retries](/guides/retries/)** - How Swytchcode retries transient failures automatically.
- **[Idempotency](/guides/idempotency/)** - Prevent duplicate operations during retries.
- **[Workspaces and teams](/guides/workspaces/)** - Personal and team workspaces, roles, seats, and per-workspace log storage.
- **[Pricing](https://www.swytchcode.com/pricing)** - Current plans, limits, and billing on the Swytchcode website.
- **[Policies Overview](/policies/overview/)** - Policy guardrails that validate every tool execution.
- **[Policy recipes](/policies/recipes/)** - Ready-to-use policies for email, payments, data safety, code, time windows, and more.
- **[Human approval](/policies/human-approval/)** - Hold high-impact commands until someone approves or denies them in Slack.
- **[tooling.json Reference](/configuration/tooling-json/)** - Define trusted methods.
- **[manifest.json Reference](/configuration/manifest-json/)** - Configure endpoints, auth, retries, and execution policies.
- **[policies.json Reference](/configuration/policy-json/)** - Apply runtime guardrails and validation rules.
- **[Runtime SDK Overview](/runtime-sdk/)** - JavaScript and Python SDKs for tool execution.
- **[JavaScript SDK](/runtime-sdk/javascript/)** - Build Node.js/Bun/Next.js agents with the runtime.
- **[Python SDK](/runtime-sdk/python/)** - Execute trusted tools from Python applications.
- **[Anthropic SDK Quickstart](/quickstarts/anthropic-sdk/)** - Connect Claude agents to trusted tools.
- **[Native SDK Quickstart](/quickstarts/native-sdk/)** - Use Swytchcode tools with provider SDKs and platforms.
- **[MCP Server Reference](/cli/mcp/)** - Set up and connect the MCP server for Cursor, Claude Code, Windsurf, Copilot, Gemini CLI, Codex, Hermes, and OpenClaw.
- **[MCP Tool Reference](/reference/mcp-reference/)** - The full tool-by-tool table for both MCP profiles (`agent`: 7 tools, `full`: 15 tools) and their CLI equivalents.
- **[CLI Command Reference](/reference/commands/)** - Every `swy` subcommand, flag, and exit code.
- **[Troubleshooting](/reference/troubleshooting/)** - Exit codes, common failure modes, and diagnostic commands.
- **[Cookbook](/cookbook/)** - Real-world agent example projects with source on GitHub.

## What `/llms.txt` includes

The published file includes:

- Product description and canonical doc links
- CLI commands for install, login, auth, and mcp management
- MCP tool profiles (`agent` vs `full`) and their per-tool CLI equivalents
- Guidance for creating and using trusted tools
- Notes on managed auth, retries, idempotency, and policies
- Links to runtime SDK docs and provider integration guides
- Community and open source links for Swytchcode

## Connecting agents via MCP

The MCP server exposes two tool profiles, selected with `--profile`:

```bash
swy mcp serve --profile agent # default: 7 tools, execution-focused (discover, info, exec, list, search, add, policy-read)
swy mcp serve --profile full # 15 tools: adds init, bootstrap, version, get, doctor, policy_check, policy_add, policy_remove
```

Most MCP-compatible editors (Cursor, Windsurf, Copilot, Gemini CLI, Codex, Hermes, OpenClaw) register the server automatically via `swy init --editor= `. Claude Code is the exception - it's registered separately with `claude mcp add`. Once connected, Swytchcode handles input validation, credential resolution, policy evaluation, retries, idempotency, and response normalization automatically for every tool call.

See the [MCP server reference](/cli/mcp/) for setup steps, the [MCP tool reference](/reference/mcp-reference/) for the full tool table, and [Troubleshooting](/reference/troubleshooting/) if a connection or execution fails.

Browse the full catalog of supported APIs at [swytchcode.com/apis](https://www.swytchcode.com/apis).

## Open source and GitHub

Swytchcode runtime components are open source and maintained in GitHub repositories, including runtime SDKs for JavaScript and Python.

## Direct link

[`https://docs.swytchcode.com/llms.txt`](/llms.txt)