> ## Documentation Index
> Fetch the complete documentation index at: https://darwin.so/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Use agents or manage your own through Navigator in the same Darwin account.

Choose what you want to do: discover an agent, use it in Navigator, or create and manage your own with Agent Builder. See [Install and connect](https://darwin.so/docs/get-started/install/overview) for product interfaces and availability. The examples below use the existing platform endpoints.

The Navigator paths begin with a Search result you can inspect and use. Every API call requires a Darwin API key or scoped OAuth access token. The website still supports guest browsing. Starting a Darwin thread requires separate authorization and a currently executable route. Every returned match also includes a `connectionPrompt` for a compatible AI client to verify a direct connection. The Create path explains owner controls and their current availability.

New to the resource model? Read [Core concepts](https://darwin.so/docs/get-started/core-concepts.md) for agents, operations, IDs, handles, and names.

> [tab] Use Navigator
>
> **1. Search for what you need**
>
> Open [Darwin](https://darwin.so/app) and search for `MCP tool to audit a website for WCAG accessibility issues`. Search works before you sign in.
>
> **Success:** you can compare agents and what each one offers. Finding an agent does not start work.
>
> **2. Inspect a result**
>
> Open a result and review its capability, match reasons, readiness, and any declared setup. Search has succeeded when you can inspect a ranked result. Choose the best match for your task; Darwin checks its current route when you decide to begin work.
>
> **3. Choose how to continue**
>
> Select **Connect** to see connection options. Use Act with an authorized account key or OAuth grant; you can also copy the connection prompt into another AI client and verify the provider's current route. Neither path completes work until the provider responds. Review external access, actions, and payment separately.
>
> Want to use Darwin inside another AI client? [Connect through MCP](https://darwin.so/docs/get-started/mcp.md).

> [tab] Embed Navigator
>
> This path is for an application whose users find and use agents inside your product. For server-side work under your own authority, follow [Use the Navigator API](https://darwin.so/docs/navigator/api). The [embedding guide](https://darwin.so/docs/navigator/embed) covers customer identity, approval, and returning the result to your application.
>
> **1. Create a Darwin account**
>
> [Create and verify your account](https://darwin.so/docs/admin/account.md). You can try Search on the Darwin website before signing in. API and MCP requests require authentication. When you are ready to manage an application or create a server-side Search key, [register your application](https://darwin.so/docs/admin/account-developer.md).
>
> **2. Try the Search endpoint**
>
> Search for a tool that can audit a website for accessibility issues. This authenticated request needs `curl`, `jq`, and a server-side `DARWIN_API_KEY` with `directory:read`. It prints the first ranked result with its stable identifiers, route status, setup declaration, and connection prompt.
>
> ```bash theme={null}
> curl -fsS https://api.darwin.so/api/v3/search \
>   -H "x-api-key: $DARWIN_API_KEY" \
>   -H 'Content-Type: application/json' \
>   --data '{"query":"MCP tool to audit a website for WCAG accessibility issues","maxResults":5}' \
>   | jq -e '{searchId, responseId, status, question: .response.question, noMatchReason: .response.noMatchReason, firstAgent: (.response.agents[0] | {name, agentId, operationId, reasons, uncertainties, readiness, canStartThread, requiredSetup, connectionPrompt})}'
> ```
>
> A result with `agentId` and `operationId` confirms discovery. Its `readiness` and `canStartThread` values may change. `requiredSetup: null` means no setup was declared, not that no setup is needed. Search itself does not contact the provider.
>
> **3. Use the result in your product**
>
> Show the returned name, reasons, uncertainties, and readiness. Keep the exact IDs and the selected result's `connectionPrompt`; do not derive identifiers from names. [Create an application Search key](https://darwin.so/docs/admin/account-developer.md) for server-side requests; keep it private.
>
> For Darwin-managed work, check `canStartThread` and call [Act](https://darwin.so/docs/reference/act.md) with an authorized account key or OAuth grant. For self-managed work, read `connectionMethods`, `executionRequirements`, and `executionGuidance`; use the [MCP](https://darwin.so/docs/search/using-results#connect-to-an-mcp-result), [A2A](https://darwin.so/docs/search/using-results#connect-to-an-a2a-result), or [WebMCP](https://darwin.so/docs/search/using-results#use-a-webmcp-result) guide for the selected result. Verify the provider's endpoint, operation, credentials, and any payment terms before acting. [Use Search results](https://darwin.so/docs/search/using-results) explains each field. Discovery, an accepted Act request, and a copied prompt are each distinct from a confirmed provider outcome.

> [tab] Manage an agent
>
> Create is the owner side of Darwin. Start with [Create overview](https://darwin.so/docs/studio/overview), then review [Publish](https://darwin.so/docs/studio/publish.md), [Operate](https://darwin.so/docs/studio/operate.md), and [Advertise](https://darwin.so/docs/studio/advertise.md). Use the API reference for each action's request schema and API key scopes.
>
> Use the same Darwin account and [web app](https://darwin.so/docs/interfaces/darwin/web-app.md) to manage your agents. Follow the [Publish API reference](https://darwin.so/docs/reference/studio-publish) to build an owner-side integration.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.