20 Best Web Scraping MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for Web Scraping

The ranking, with the evidence

• 1

  actors-mcp-server

  Community favourite

  apify/apify-mcp-server ↗

  Best for: Web scraping tasks that fit existing Apify Actors: it exposes tools to search the Apify Store, inspect Actor details, call Actors, and read results.

  The server exposes 13 tools for searching the Apify Store, fetching Actor details, calling Actors, and retrieving Actor run outputs from datasets and key-value stores. The hosted endpoint uses Apify OAuth or an API token for authentication, and running it locally over stdio requires the @apify/actors-mcp-server npm package.

  Score 95.4: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • npm downloads92
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum79 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • npm download trend14
  • Tool quality88 / 100 · weight 13%
    • Tool description quality80
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  95.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  95.4

• 2

  Firecrawl MCP Server

  Community favourite

  firecrawl/firecrawl-mcp-server ↗

  Best for: For extracting content from a known URL into Markdown or JSON matching a supplied schema, firecrawl_scrape is the direct fit.

  The Firecrawl MCP Server provides tools to scrape a URL into Markdown, HTML, links, screenshots, or JSON matching a supplied schema; parse PDFs and documents; map and crawl sites; search the web, developer sources, government sources, and scientific papers; interact with pages in a browser; run agent research jobs; monitor pages; and check credit usage. The hosted keyless endpoint exposes firecrawl_scrape, firecrawl_search, and firecrawl_parse; other tools such as firecrawl_crawl, firecrawl_map, and firecrawl_agent require an API key.

  Score 93.2: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars97
    • npm downloads50
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance95 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence100
  • Momentum85 / 100 · weight 14%
    • Stars gained, relative to size70
    • Stars gained, absolute95
    • npm download trend100
  • Tool quality73 / 100 · weight 13%
    • Tool description quality65
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  93.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  93.2

• 3

  Bright Data MCP

  Community favourite

  brightdata/brightdata-mcp ↗

  Best for: When an agent must fetch pages that block ordinary HTTP clients and drive a browser session: it exposes scraping and browser automation tools over MCP.

  Bright Data MCP exposes 32 tools for web search, page scraping as Markdown or HTML, structured data extraction, browser automation, and collecting ChatGPT and Perplexity responses through MCP. Choosing it requires a Bright Data API token, supplied either in the hosted server URL or in the API_TOKEN environment variable for the local npx package.

  Score 88.4: show every number behind it

  • Adoption92 / 100 · weight 40%
    • GitHub stars86
    • npm downloads42
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum69 / 100 · weight 14%
    • Stars gained, relative to size53
    • Stars gained, absolute68
    • npm download trend100
  • Tool quality68 / 100 · weight 13%
    • Tool description quality60
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  88.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  88.4

• 4

  X Twitter Scraper

  Community favourite

  Xquik-dev/x-twitter-scraper ↗

  Best for: Setting up Xquik's hosted X/Twitter MCP from a portable Agent Plugins package: explore and xquik return setup guidance, not live scraping.

  X Twitter Scraper is a portable Agent Plugins package for a hosted MCP server, exposing explore for API catalog search and xquik for approved requests; the included package stubs return setup guidance only. Before choosing it, note that private reads and X account actions require a connected X account, while the documented REST request uses an XQUIK_API_KEY.

  Score 81.1: show every number behind it

  • Adoption63 / 100 · weight 40%
    • GitHub stars59
    • npm downloads27
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum84 / 100 · weight 14%
    • Stars gained, relative to size96
    • Stars gained, absolute53
    • npm download trend100
  • Tool quality85 / 100 · weight 13%
    • Tool description quality77
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  81.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  81.1

• 5

  wigolo

  Community favourite

  KnockOutEZ/wigolo ↗

  Best for: Web research or data gathering where local cache reuse matters: it exposes cache, search, fetch, crawl, extract, research, and agent tools.

  wigolo is a local-first MCP server that exposes ten tools for search, fetching, crawling, structured extraction, cache lookup, similar-content discovery, multi-step research, autonomous agent loops, markdown diffs, and persistent watch jobs. Before choosing it, note that setup requires Node 20 or newer and about 1.5 GB of free disk space.

  Score 72.6: show every number behind it

  • Adoption98 / 100 · weight 40%
    • GitHub stars94
    • npm downloads32
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum69 / 100 · weight 14%
    • Stars gained, relative to size47
    • Stars gained, absolute76
    • npm download trend100
  • Tool quality85 / 100 · weight 13%
    • Tool description quality77
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  93.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  72.6

• 6

  docs-mcp-server

  Community favourite

  arabold/docs-mcp-server ↗

  Best for: Version-specific search over third-party library docs: it indexes a website, repository or package per library version and serves full-text plus optional vector search.

  The server scrapes websites, GitHub repositories, npm, PyPI packages, local folders and archives into a local SQLite index and serves search over MCP (stdio or Streamable HTTP), plus a command line and a web UI. Vector search requires an embedding provider such as OpenAI or a local Ollama instance, and embeddings are only computed at index time, so docs scraped without a model need a re-scrape with replacement to gain vectors.

  Score 69.3: show every number behind it

  • Adoption87 / 100 · weight 40%
    • GitHub stars82
    • npm downloads34
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum84 / 100 · weight 14%
    • Stars gained, relative to size81
    • Stars gained, absolute76
    • npm download trend100
  • Tool quality≈73 / 100 · weight 13%
    • Tool description quality≈73
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  88.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  69.3

• 7

  webclaw

  Community favourite

  0xMassi/webclaw ↗

  Best for: Scraping bot-protected pages without a headless browser: it uses TLS fingerprinting to fetch content and returns LLM-optimized markdown.

  webclaw exposes 10 MCP tools covering single-page scrape, crawl, URL map, batch fetch, LLM-based extraction and summarization, content diffing, brand identity extraction, web search, and research, and its README also documents a CLI, REST API, and SDKs. Search and research require a WEBCLAW_API_KEY, and several tools fall back to the hosted webclaw cloud API when bot protection is detected.

  Score 67.8: show every number behind it

  • Adoption85 / 100 · weight 40%
    • GitHub stars85
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum71 / 100 · weight 14%
    • Stars gained, relative to size69
    • Stars gained, absolute75
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality78 / 100 · weight 13%
    • Tool description quality70
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  86.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.8

• 8

  crw-mcp

  Community favourite

  fastcrw/crw ↗

  Best for: AI agents that need self-hosted scraping and extraction: it exposes 8 tools for scraping, crawling, mapping, structured JSON extraction, and local PDF parsing.

  crw-mcp exposes 8 tools for scraping a URL into markdown, HTML, or links, crawling a site, mapping URLs, extracting structured JSON via an async job, parsing local PDFs, checking crawl and extract status, and cancelling extract jobs. Before choosing it, note that structured extraction needs an LLM and local PDF parsing has no OCR, so scanned PDFs return empty markdown with a warning.

  Score 67.8: show every number behind it

  • Adoption77 / 100 · weight 40%
    • GitHub stars77
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum94 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute86
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality76 / 100 · weight 13%
    • Tool description quality68
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  86.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.8

• 9

  SpotifyScraper MCP Server

  Abandoned but popular

  AliAkhtari78/SpotifyScraper ↗

  Best for: Scraping public Spotify metadata without an API key: it exposes tools for tracks, albums, artists, playlists, podcasts, lyrics, related artists, and batch fetches.

  It exposes 28 tools that fetch Spotify tracks, albums, artists, playlists, shows, and episodes by URL, URI, or ID, alongside search, editorial charts, related artists, discographies, batched multi-item lookups, and cover colour extraction. Public data needs no API key or OAuth, but lyrics, podcast transcripts, credits, canvas videos, and account state require the caller's own sp_dc cookie passed as SPOTIFY_SP_DC, and the scope is Spotify entities only rather than general web pages.

  Score 64.7: show every number behind it

  • Adoption68 / 100 · weight 40%
    • GitHub stars63
    • PyPI downloads34
      PyPI downloads show no weekday rhythm; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance46 / 100 · weight 24%
    • Last commit touching this server68
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 48 days ago, which counts every ref; the stored date would have published 48 days ago
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size60
    • Stars gained, absolute42
    • PyPI download trend100
  • Tool quality66 / 100 · weight 13%
    • Tool description quality57
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  64.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  64.7

• 10

  proxy-scraper

  Steady

  maximilianfeix/proxy-scraper ↗

  Best for: Scraping pages from outside the agent's own IP: fetch_url loads them through verified free proxies, falling back to the next proxy on failure.

  It exposes three tools: get_proxies returns the published proxy list fastest first, check_proxies re-runs the handshake and content checks from the local machine's network, and fetch_url loads a page through a verified proxy and returns it as readable text. The proxies themselves are public and run by strangers, and the published list is checked from GitHub's servers about every hour rather than from the caller's network, so check_proxies is the step to run before trusting a proxy for anything.

  Score 63.4: show every number behind it

  • Adoption51 / 100 · weight 40%
    • GitHub stars47
    • PyPI downloads27
      PyPI downloads show no weekday rhythm; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute65
    • PyPI download trend0
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  74.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  63.4

• 11

  searxNcrawl

  Community favourite

  DasDigitaleMomentum/searxNcrawl ↗

  Best for: Teams that need web search via SearXNG plus Markdown page or site crawling: it exposes search, crawl, and crawl_site tools.

  searxNcrawl exposes 3 tools: crawl extracts one or more URLs to Markdown or JSON, crawl_site crawls an entire website from a seed URL using DFS, and search queries configured SearXNG and/or You.com providers in parallel. Before choosing it, note that the search tool needs a SearXNG instance with JSON output enabled and/or a You.com API key, though crawling works without either.

  Score 62.0: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars57
    • PyPI downloads51
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum83 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute57
    • PyPI download trendnot measured
      no download history for the selected registry
  • Tool quality71 / 100 · weight 13%
    • Tool description quality63
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  79.5

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  62.0

• 12

  Equibles

  Emerging

  daniel3303/Equibles ↗

  Best for: AI agents needing scraped SEC and market data: it exposes 65 tools for filings, 13F holdings, insider trades, short data, macro indicators and prices.

  Equibles is a self-hosted financial-data MCP server exposing 65 tools for SEC filing search, XBRL financial statements, 13F institutional holdings, insider and congressional trades, FINRA/SEC short data, FRED economic indicators, CFTC positioning, VIX history, and daily stock prices. It is designed to run on the user's own hardware with Docker, and no npm package is published, so installation means deploying the Docker service rather than adding a package.

  Score 59.8: show every number behind it

  • Adoption60 / 100 · weight 40%
    • GitHub stars60
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum67 / 100 · weight 14%
    • Stars gained, relative to size79
    • Stars gained, absolute48
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  76.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  59.8

• 13

  doc-scraper

  Steady

  Sriram-PR/doc-scraper ↗

  Best for: Agents needing offline search and page reads over a configured documentation corpus: doc-scraper exposes crawl_site, search_docs, and read_page over local Markdown/JSONL.

  doc-scraper is a self-hosted MCP server that exposes 13 tools for configuring documentation sites, starting and monitoring crawls, searching and reading the stored Markdown corpus offline, checking freshness, diffing crawl changes, and fetching individual pages live. Before choosing it, note that offline search and read_page depend on configuring a site and completing a crawl, and the project is scoped to documentation sites rather than arbitrary web scraping.

  Score 59.6: show every number behind it

  • Adoption51 / 100 · weight 40%
    • GitHub stars51
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum35 / 100 · weight 14%
    • Stars gained, relative to size43
    • Stars gained, absolute24
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality91 / 100 · weight 13%
    • Tool description quality83
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  70.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  59.6

• 14

  read-website-fast

  Community favourite

  just-every/mcp-read-website-fast ↗

  Best for: Reading documentation pages into clean Markdown for an AI agent: the read_website tool extracts content with Mozilla Readability and caches by URL.

  The server exposes one read_website tool that fetches a webpage and converts it to clean Markdown, with optional multi-page crawling. It depends on @just-every/crawl for its core crawling and Markdown conversion.

  Score 58.6: show every number behind it

  • Adoption66 / 100 · weight 40%
    • GitHub stars55
    • npm downloads58
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance92 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence85
  • Momentum47 / 100 · weight 14%
    • Stars gained, relative to size35
    • Stars gained, absolute21
    • npm download trend100
  • Tool quality85 / 100 · weight 13%
    • Tool description quality77
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  75.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.6

• 15

  Crawlberg MCP Server

  Emerging

  xberg-io/crawlberg ↗

  Best for: Crawling JavaScript-heavy public sites into Markdown: the README documents a headless-browser fallback for JavaScript rendering and HTML-to-Markdown conversion.

  The README documents a crawler and scraper that can be driven from code, an AI agent, a REST service, or the CLI, fetching pages, following links, converting HTML to Markdown, and returning structured metadata. Before choosing it, note that managed features such as proxy pools, tuned bot evasion, authenticated sessions, scheduling, and billing are documented as living in xberg-enterprise.

  Score 58.6: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars57
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum70 / 100 · weight 14%
    • Stars gained, relative to size84
    • Stars gained, absolute48
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈73 / 100 · weight 13%
    • Tool description quality≈73
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  75.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.6

• 16

  LinkedIn MCP Server

  Emerging

  eliasbiondo/linkedin-mcp-server ↗

  Best for: Scraping LinkedIn profiles, companies, and jobs from an AI client: it exposes seven browser-automation tools for people, company, and job data.

  LinkedIn MCP Server provides seven MCP tools for retrieving person profiles and searching people, retrieving company profiles and posts, retrieving job details and searching jobs, and closing the browser. It assumes a local browser-automation setup: a LinkedIn account, Python and uv, Patchright browser binaries, and a persisted login are required.

  Score 57.9: show every number behind it

  • Adoption58 / 100 · weight 40%
    • GitHub stars58
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance83 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence40
  • Momentum83 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute57
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  74.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.9

• 17

  servo-fetch

  Steady

  konippi/servo-fetch ↗

  Best for: Scraping JavaScript-heavy pages in a Chromium-free environment: servo-fetch fetches rendered content, executes JavaScript, crawls same-site links, and takes software-rendered screenshots.

  servo-fetch exposes six MCP tools for batch fetching, readable extraction, JavaScript execution, same-site crawling, URL mapping, and software-rendered screenshots, and its README also documents CLI, Rust, Python, and Node.js interfaces. On Linux headless servers, the README requires the runtime libraries libegl1, libfontconfig1, and libfreetype6 plus xvfb-run.

  Score 57.6: show every number behind it

  • Adoption55 / 100 · weight 40%
    • GitHub stars55
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum52 / 100 · weight 14%
    • Stars gained, relative to size63
    • Stars gained, absolute37
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality88 / 100 · weight 13%
    • Tool description quality80
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  73.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.6

• 18

  Search1API MCP Server

  Community favourite

  superagents-lab/search1api-mcp ↗

  Best for: Answering questions from current web pages and sites: it exposes search, news, crawl, sitemap, trending, maps, and deepcrawl tools for finding and reading sources.

  Search1API MCP Server exposes 10 tools: search, news, crawl, sitemap, trending, ask, maps, deepcrawl, render_results, and send_feedback. Before choosing it, note that every MCP request, including tool discovery, requires a Search1API credential through OAuth or an API key.

  Score 57.1: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars56
    • npm downloads54
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum25 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trend100
  • Tool quality85 / 100 · weight 13%
    • Tool description quality77
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  73.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.1

• 19

  SeleniumBase MCP

  Community favourite

  seleniumbase/SeleniumBase ↗

  Best for: Scraping sites protected by anti-bot systems: it exposes 24 browser-control tools including CDP Mode and CAPTCHA attempts.

  SeleniumBase MCP exposes 24 tools for persistent CDP Mode browser sessions, navigation and history, element discovery and content extraction, page interaction, waits and assertions, cookies and storage, tabs and windows, page saving, CAPTCHA attempts, and JavaScript execution. Before choosing it, note that browser interaction tools assume an active session started with start_browser and closed with close_browser when the workflow finishes.

  Score 57.0: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • PyPI downloads50
      PyPI downloads show no weekday rhythm; halved
    • Used through Glama61
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size50
    • Stars gained, absolute92
    • PyPI download trend57
  • Tool quality100 / 100 · weight 13%
    • Tool description quality93
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  95.0

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.0

• 20

  Stealth Browser MCP

  Community favourite

  vibheksoni/stealth-browser-mcp ↗

  Best for: Scraping sites behind Cloudflare challenges or login walls: it drives real Chrome-family browsers through nodriver and CDP to get past anti-bot checks.

  It runs a local MCP server that drives real Chrome, Chromium or Edge instances over nodriver and the Chrome DevTools Protocol, exposing tools for navigation, pixel-accurate element extraction, network request inspection, and JavaScript or CDP execution, with modular sections that can be loaded in full or cut down to a core set. Before installing, note that it needs Python 3.10+ plus a locally installed Chrome-family browser, and that the PyPI package is named browserstealthmcp because the similarly named stealth-browser-mcp package on PyPI is an unrelated project.

  Score 56.8: show every number behind it

  • Adoption96 / 100 · weight 40%
    • GitHub stars88
    • PyPI downloads51
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum100 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • PyPI download trendnot measured
      no download history for the selected registry
  • Tool quality≈73 / 100 · weight 13%
    • Tool description quality≈73
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  94.7

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.8

Questions people ask

Other comparisons

• Best Figma MCP servers
• Best Obsidian MCP servers
• Best YouTube MCP servers
• Best Jira MCP servers
• Best PostgreSQL MCP servers
• Best MySQL MCP servers
• Best GitHub MCP servers
• Best Notion MCP servers
• Best Linear MCP servers
• Best Discord MCP servers
• Best MongoDB MCP servers
• Best CRM MCP servers
• Best Payments MCP servers
• Best Ecommerce MCP servers
• Best Social Media MCP servers
• Best Browser Automation MCP servers
• Best Email MCP servers
• Best PDF MCP servers
• Best Kubernetes MCP servers
• Best Docker MCP servers
• Best AWS MCP servers
• Best Spreadsheets MCP servers
• Best SEO MCP servers
• Best Web Search MCP servers
• Best Vector Database MCP servers
• Best Code Execution MCP servers
• Best Calendar MCP servers
• Best Observability MCP servers
• Best Image Generation MCP servers
• Best Speech & Transcription MCP servers
• Best Maps MCP servers
• Best Travel MCP servers
• Best Stock Market MCP servers
• Best Web Analytics MCP servers
• Best Memory MCP servers
• Best Documentation MCP servers
• Best Security MCP servers