webCrawl

Crawl and ingest web pages into a knowledge base using sitemap.xml, accepting a URL and optional read limit. Executes asynchronously and returns a feed identifier for streamlined data organization.

Instructions

Crawls web pages from web site into Graphlit knowledge base. Accepts a URL and an optional read limit for the number of pages to crawl. Uses sitemap.xml to discover pages to be crawled from website. Executes asynchronously and returns the feed identifier.

Input Schema

Name	Required	Description	Default
`readLimit`	No	Number of web pages to ingest, optional. Defaults to 100.
`url`	Yes

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "readLimit": {
      "description": "Number of web pages to ingest, optional. Defaults to 100.",
      "type": "number"
    },
    "url": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "type": "object"
}

Graphlit MCP Server

webCrawl

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Graphlit MCP Server

Related Tools