Returns the state of a crawl that web_crawl_start started, and its pages, 10 at a time. Use it when web_crawl_start says the crawl is still running, or to read the next pages. It only reads: it does not start or change a crawl.

Inputs

Name	Type	Default	Allowed values	Description
`crawlId`required	`string`	–	–	The crawl's id, from `web_crawl_start`.
`after`	`string`	–	–	The cursor from the last result (its last line says `after "…"`), to read the pages that follow. Leave it out for the first pages.

Example call

This is what an MCP client sends. You do not write it yourself: ask the model in plain words and it calls the tool.

tools/call

{  "name": "web_crawl_get",  "arguments": {    "crawlId": "crawl_2Gh7Kx0Lq9Zp4Nm3"  }}

What it returns

The same report as web_crawl_start: the crawl's status and counts, up to 10 pages, and a last line that either says to call web_crawl_get again or says every page has been read.

Result

Crawl crawl_2Gh7Kx0Lq9Zp4Nm3 of https://example.com/docs: running; 12 pages read, 0 failed, 0 skipped by robots.txt.## Installhttps://example.com/docs/install (HTTP 200, depth 1)…The crawl is still running: call web_crawl_get with crawlId "crawl_2Gh7Kx0Lq9Zp4Nm3" in a few seconds.

When a call fails, the result is marked as an error. Its text starts with the API’s error code, such as unauthorized or session_not_running, followed by its message.

Annotations

The server tells every client what this tool does to the world, so a client can decide what to ask you about before it runs.

Annotation	Value
`title`	Get a crawl's pages
`readOnlyHint`	`true`
`destructiveHint`	`false`
`openWorldHint`	`false`

Good to know

Pass the after that the last result gave to read the next pages. The crawl keeps running in the background while you read.

The same thing with the API

Endpoint	Reference
`GET /v1/crawls/{id}`	Get a crawl

These docs describe a beta API. Endpoints, fields and SDK methods may change before general availability; breaking changes will be listed in the changelog.