Read a web page
web_fetchRead one page of the public web, given its address: its words as Markdown, with the e-mail addresses, phone numbers and named people the page publishes. A long page comes back in parts (next_start), or as only the passages that hold the words in find. Reads pages, not files: a PDF is not read. Members only.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "web_fetch"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The page's full address: one a search returned, one on a record in the database, or one the person gave. | |
| find | No | Words to look for on the page; several ways of saying it split with "|" ("managing partner|founder|principal"). Only the passages that hold them come back, each with the lines around it. Use it on a long page when one thing is wanted. | |
| start | No | Where to start reading, in characters: the next_start of a page that was cut, to read on. |