Skip to content

MCP servers for web scraping without a repository URL

Of the 346 MCP servers in the measured field of use Web scraping, the registry lists no repository URL for 121 – markedly more than the 78 the comparison group would lead one to expect.

121 servers 0.4% of 26,983 in the directory

This category in numbers

The most frequent value per property, counted across the entries of this category. The full distribution is further down.

Entries

Filter further

Entries 1 to 50 of 121

Entries
AI Crawler Indexdev.workers.pathwren.www/ai-crawler-index
AgentMart Procurementonline.agentmart/procurement
Amazon Reviews Scraper - Extract Product Datacom.ranovam/amazon-review-intelligence
Andi Searchcom.andiai/andi-search
Ashby Job Scraper & API for Team Job Boardscom.ranovam/ashby-scraper
Atlassian Statuspage Scraper & JSON API Toolcom.ranovam/statuspage-scraper
Brainiall Webcom.brainiall/web
Crawler IP Verifier - real Googlebot or fakedev.workers.pathwren.www/crawler-ip-verifier
Crawler Log Triagedev.workers.pathwren.www/crawler-log-triage
Cromacom.usecroma/croma
Data Enrichment & Web Scraper APIio.github.Mila-Petrovich/data-enrichment
Data Quality Gate - deterministic post-scrape cleaner + verdictio.github.aidatatools-dev/data-quality-gate
Discourse Forum Scraper — Topics & Postscom.ranovam/discourse-forum-scraper
Domduckcom.domduck/domduck
Execute behance-portfolio-scraper-mcpio.github.Evozim/behance-portfolio-scraper-mcp
EzBiz SEO & Marketing Analysiscom.ezbizservices/seo-marketing
FUTIAio.futia/seo
Fastcrawlnet.fastcrawl/fastcrawl
Google Maps Business Contact Email Scrapercom.ranovam/maps-contact-cleaner
Google Maps Real Estate Agency Data Scrapercom.ranovam/realestate-agency-maps-scraper
Goroai.usegoro/goro
Greenhouse Jobs Scraper & API Data Extractorcom.ranovam/greenhouse-jobs-scraper
GroundAPIio.github.qingkongzhiqian/groundapi
H/M Blindspot Challenge Platformnet.hogarmas/blindspot
Hydrafetchcom.hydrafetch/web
IDLE Protocolcom.earnidle/mcp
Instagram Hashtag Posts & Reels Scraper APIcom.ranovam/instagram-hashtag-discovery
Instatus Status Page Scraper – JSON API Toolcom.ranovam/instatus-scraper
Iskat — Russian-language web search for agentsio.iskat/webdex
Kai AGI - Autonomous AI Agentcom.kai-agi.mcp/kai-agi
Kai AGI - Autonomous AI Agentcom.trycloudflare.annotated-lot-operational-tourism/kai-agi
Lever Jobs Scraper - Job Board Data Extractorcom.ranovam/lever-scraper
LexLint: compliance lint for AI, scraping, and privacy laworg.lexlint/lexlint
LinkedIn Lead Enrichment & Data Scraper APIcom.ranovam/ai-lead-enricher-personalizer
LinkedIn Profile Data Scraper & Extractor Toolcom.ranovam/vertical-lead-pack
MESSORAdev.messora/messora
Olostep MCP Serverio.github.olostep/olostep-mcp-server
Open Collective Expenses & Transactions Scrapercom.ranovam/opencollective-scraper
Pa1m SEOio.github.retampweb/pa1m-seo
Perplexity API Platformai.perplexity/mcp-server
Perplexity API Platform (moved to ai.perplexity/mcp-server)io.github.perplexityai/mcp-server
Personio Jobs Scraper - Clean JSON API Toolcom.ranovam/personio-scraper
Pinpoint Jobs Scraper - Job Board API Toolcom.ranovam/pinpoint-scraper
Prowl MCPchat.prowl/prowl-mcp
Recruitee Jobs Scraper - Clean Job Data APIcom.ranovam/recruitee-scraper
SE Rankingcom.seranking/mcp
SEEK Jobs Scraper: Australia & NZ Listingscom.ranovam/seek-scraper
ScrapeNestdev.scrapenest/scrapenest
Scrappycocoio.github.Albert-Tam/scrappycoco
SeaWebtech.seaweb/seaweb

All 121 entries in the list, with filters and pagination

What this category selects

What this category selects
Field of use, derived from the vendor descriptionWeb scraping
derived from: Description (raw)
Repository URL listedno
derived from: Repository (raw)

A derived value carries its original data beside it; the derivation rule is published, with a version, on the methodology page.

Caveats, distribution and query

What this category does not say

  • Field of use, derived from the vendor description is not declared but computed: from Description (raw). The rule is published, with a version, on the methodology page.
  • Repository URL listed is not declared but computed: from Repository (raw). The rule is published, with a version, on the methodology page.

What is measured is what a manifest declares, not what a piece of software does. This registry fetches no repository URL, no endpoint and no package index; nothing here is verified. Which value comes from which source, and by which rule it was formed, is set out in the Methodology.

Every sentence here follows from the condition above, not from an assessment.

How this category is distributed

Required secrets declared

121
Required secrets declared
no80 66 %
yes41 34 %

Icon formats (raw)

121
Icon formats (raw)
nothing declared91 75 %
image/png23 19 %
image/svg+xml5 4.1 %
image/png, image/svg+xml1 0.8 %
image/svg+xml, image/webp1 0.8 %

Schema version of the raw record (raw)

121
Schema version of the raw record (raw)
https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json104 86 %
https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json15 12 %
https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json1 0.8 %
https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json1 0.8 %

Execution location

121
Execution location
remote111 92 %
local10 8.3 %

Delivery form (raw)

121
Delivery form (raw)
remote111 92 %
package8 6.6 %
package and remote2 1.7 %

Per property, the measured values inside this category. The share refers to the 121 entries of the category, not to the registry.

The same category through the interface

curl -s "https://api.tracevero.com/v1/eintraege?art=mcp_server&einsatzgebiet=websammlung&quelloffen_einsehbar=false&grenze=200"

The command carries exactly the condition of this page. 121 entries at 200 each are a single request; the total is in the X-Gesamt header.

Changes to these entries

https://tracevero.com/aenderungen.atom?thema=einsatz-websammlung-ohne-repository

Both addresses narrow the change stream to exactly the entries in this category. The feed carries an identifier of its own, so a feed reader keeps it apart from the full stream.

Categories sharing entries with this one

MCP servers for web scraping 346 entries in this category121 shared Remote MCP servers with an Authorization header 1,303 entries in this category32 shared Remote MCP servers with declared required secrets 1,491 entries in this category36 shared Remote MCP servers without a repository URL 5,777 entries in this category111 shared MCP servers without a repository URL 6,432 entries in this category121 shared MCP servers for social media 396 entries in this category8 shared

Per neighbour its own size and the counted number of shared entries. An category without a single shared entry is not listed here.

tracevero · https://tracevero.com/themen/einsatz-websammlung-ohne-repository