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

# Create Web Source

> Add a new web source to an agent's knowledge base.

## Endpoint

```
POST /web-sources
```

## Authentication

Required.

## Request body

<ParamField body="agentId" type="string" required>
  The agent ID.
</ParamField>

<ParamField body="url" type="string" required>
  The URL to crawl. Must be a valid HTTP or HTTPS URL.
</ParamField>

<ParamField body="mode" type="string" required>
  Crawl mode: `crawl` (recursive), `sitemap` (discover from sitemap), or `single` (one page only).
</ParamField>

<ParamField body="maxPages" type="number">
  Maximum number of pages to crawl. Range: 1–100. Default: `50`.
</ParamField>

<ParamField body="maxDepth" type="number">
  Maximum crawl depth for link following. Range: 1–3. Default: `2`.
</ParamField>

## Response

<ResponseField name="success" type="boolean" />

<ResponseField name="webSource" type="object">
  The created web source object (see [List Web Sources](/api-reference/web-sources/list) for the full shape).
</ResponseField>

## Limits

* Maximum **10 web sources** per agent.

## Example

```bash theme={null}
curl -X POST https://api.mind-e.co/web-sources \
  -H "Authorization: Bearer sk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "agent-id-here",
    "url": "https://example.com/docs",
    "mode": "crawl",
    "maxPages": 20,
    "maxDepth": 2
  }'
```