ScrapeSelect MCP server

• Registry namecom.scrapeselect/scrapeselectverified in the MCP registry

The registry name sits under scrapeselect.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-21
• Tools6
• Server calls itselfScrapeSelect
• Server version1.0.1
• Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 267 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer320 ms
• Space in an agent's context≈ 2,314 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsC · 72 of 100
• Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 4 of 6
• Not saying whether it only reads or can destroy: 6 of 6

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_providers

  Find scraping providers and products by name or category (scraping_api, web_unlocker, browser_api, scraping_platform).

• get_provider

  A provider's products and sources, or with `product`, that product's plans, rate tables, limits, capabilities, price history and the official source of each fact.

• compare_products

  Compare up to three products on one workload: monthly cost range, chosen plan, capabilities, limits and caveats.

• estimate_cost

  Monthly cost (low / expected / high) of a workload on each product, with the cheapest plan that fits, rejected plans and every assumption used.

• recommend_scraping_stack

  Recommend an architecture and up to three providers for a workload, with fit scores, cost ranges, reasons, limitations, assumptions and evidence URLs. Same input as POST /api/v1/recommend.

• get_recent_changes

  Price, plan and limit changes confirmed against official pages, newest first.