Crawlora MCP

Official

Overview Schema Source Related Servers Discussions Admin

datasets_techstack_search

Instructions

Search the website tech-stack dataset. Searches the website tech-stack index (dataset id enum value techstack) — one record per site listing the web technologies it is built with (frameworks, CMS, e-commerce, analytics, CDNs, servers, and more), BuiltWith / Wappalyzer-style. The reverse-index filters are the point: repeat technology to require several at once (AND), any_of to match at least one (OR), and not to exclude — e.g. sites on Shopify and Klaviyo but not Recharge. Sort enum: relevance, rank_asc, tech_count_desc, domain_asc, crawled_desc. render_tier enum: http, browser. Billing: this search costs 1 credit per record returned, with a minimum of 2 (an empty result costs 2, a full page of 100 costs 100).

Input Schema

Name	Required	Description
`q`	No	Substring match on the site domain, max 256 characters
`cdn`	No	Exact CDN / hosting filter, e.g. Cloudflare, Fastly, Vercel
`cms`	No	Exact CMS filter, e.g. WordPress, Shopify, Webflow
`not`	No	Repeatable exact technology name the site must NOT use (excludes)
`tld`	No	Exact top-level-domain filter, e.g. com, org, io
`page`	No	Page number, defaults to 1
`sort`	No	Sort enum: relevance, rank_asc, tech_count_desc, domain_asc, crawled_desc
`any_of`	No	Repeatable exact technology name; the site must use at least one (OR)
`run_id`	No	Scan run id; defaults to the latest run
`category`	No	Exact category filter, e.g. Ecommerce, CMS, Analytics, Payment, CDN
`ecommerce`	No	Exact e-commerce platform filter, e.g. Shopify, WooCommerce, Magento
`page_size`	No	Page size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
`reachable`	No	true keeps only sites whose homepage was fetched, false only sites that could not be fetched
`technology`	No	Repeatable exact technology name the site MUST use (AND), e.g. technology=Shopify&technology=Klaviyo
`web_server`	No	Exact web-server filter, e.g. nginx, Apache, IIS
`has_captcha`	No	true keeps only sites with a detected CAPTCHA
`render_tier`	No	Fetch-tier filter. Enum: http, browser
`seed_source`	No	Source filter for where the domain was discovered, e.g. tranco
`min_tech_count`	No	Minimum number of detected technologies, 0 or greater
`server_language`	No	Exact server language / framework filter, e.g. PHP, ASP.NET, Ruby on Rails
`is_infrastructure`	No	false (the common case) excludes backend CDN/DNS/cloud-vendor hostnames that rank highly but were never meant to serve a public homepage, keeping only real, human-navigable sites; true keeps only those backend hostnames

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.17.5Sep 26, 2026
- addedInput schema / properties / any_of / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / not / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / render_tier / enum
```
Added value: +[
+  "http",
+  "browser"
+]
```
- addedInput schema / properties / sort / enum
```
Added value: +[
+  "relevance",
+  "rank_asc",
+  "tech_count_desc",
+  "domain_asc",
+  "crawled_desc"
+]
```
- addedInput schema / properties / technology / items
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedv1.16.0Aug 29, 2026

addedInput schema / properties / is_infrastructure

Added value: +{
+  "description": "false (the common case) excludes backend CDN/DNS/cloud-vendor hostnames that rank highly but were never meant to serve a public homepage, keeping only real, human-navigable sites; true keeps only those backend hostnames",
+  "type": "boolean"
+}

Addedv1.5.0Jul 14, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and delivers useful behavioral detail: per-record credit billing with a stated minimum (2) and a costly full page (100), plus the semantics of `run_id` defaulting to the latest run and the meaning of `render_tier`. It omits auth requirements and any latency/rate-limit behavior, keeping it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then filters, enums, and billing, with every section earning its place. It is somewhat long and redundantly repeats the sort and render_tier enum values already present in the schema, which is minor waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 21-parameter, zero-required search tool with no output schema or annotations, the description supplies the essential missing context: dataset content, filter composition logic, and cost model. Pagination bounds and per-parameter constraints are left to the schema, which documents them adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds value by explaining the AND/OR/exclude composition pattern across `technology`, `any_of`, and `not` and providing a concrete multi-technology example. The sort and render_tier enums are restated from the schema, which slightly dilutes the additive value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb (Search) plus a specific resource (website tech-stack dataset, enum value `techstack`) and describes the record granularity: one record per site listing its web technologies. This clearly distinguishes it from the sibling `datasets_techstack_facets` (aggregation) and `datasets_techstack_item` (single record).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains how and why to use the reverse-index filters (`technology` for AND, `any_of` for OR, `not` to exclude) with a concrete worked example, and lists the sort and render_tier enums. It gives clear context for invocation but does not name alternative tools or state when NOT to use this search. No exclusions/alternatives means it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

datasets_techstack_search

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools