PageSift
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pagesift_scrapeA | Fetch one URL and return clean content: markdown by default, or html, rawHtml, links, images and metadata. Use it when you know the page you need. For several known URLs use pagesift_batch_scrape; to find URLs on a site use pagesift_map; to collect a whole site use pagesift_crawl. pagesift respects robots.txt and reports blocked pages as errors instead of returning their content. |
| pagesift_mapA | List the URLs of a website from its sitemaps, robots.txt and homepage links, without fetching each page. Use it to find the right page before scraping, or to plan a batch scrape. |
| pagesift_crawlA | Start a crawl job that follows links from a URL and scrapes every page found. Returns a job id right away; poll it with pagesift_crawl_status. Results can be large, so set a conservative limit and use includePaths/excludePaths to stay on topic. |
| pagesift_crawl_statusA | Get the status, progress and pages collected so far for a crawl or batch scrape job. Read-only. |
| pagesift_batch_scrapeA | Scrape a list of known URLs as one job with the same options. Returns a job id; poll it with pagesift_crawl_status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: single-page scrape, URL discovery via map, whole-site crawl, job status polling, and batch scraping. Descriptions explicitly cross-reference the alternatives, making selection straightforward.
All names use the pagesift_ prefix and snake_case, which is highly consistent. The only slight deviation is crawl_status, which is a noun/state phrase rather than a verb_noun action like the others.
Five tools are well-scoped for a web scraping service and each earns its place. There are no redundant tools, and the set covers the core workflows without bloat.
The surface covers single-page scraping, batch scraping, URL mapping, crawling, and crawl status. Minor gaps include no explicit job cancellation or deletion operation, but agents can work around these limitations.