LookaCrawler
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_web_contentC | Extract token-optimized clean Markdown content from a target website for LLM consumption. |
| batch_extract_web_contentA | Batch extract token-optimized Markdown content from multiple website URLs concurrently with aggregate token statistics. |
| extract_structured_dataC | Extract page metadata (OG tags, canonical URL, author, dates) and custom CSS selector JSON schema mapping from a website. |
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 3 tools
The three tools have clear boundaries: single content extraction, batch content extraction, and structured metadata/CSS mapping. The only soft spot is that batch and single share the same core operation, but their singular-vs-batch distinction prevents real ambiguity.
All tools use lowercase snake_case and follow a predictable extract_<object> naming pattern; batch_ is a standard parallelism modifier on the same verb. There are no mixed conventions or vague verbs.
Three tools is appropriate for a narrowly scoped extraction server: one direct, one batched, and one structured metadata. It is not bloated, and slightly minimal but credible for this purpose.
Core extraction workflow is covered: single page, batch pages, and structured metadata. However, the crawler name implies link discovery or site traversal, and no tool enumerates links or sitemaps, so agents need URLs supplied beforehand. This is a notable but not deabilitating gap.