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

The short answer

Which one, for your situation

Top MCP servers for Web Search

The ranking, with the evidence

• 1

  Brave Search MCP Server

  Community favourite

  brave/brave-search-mcp-server ↗

  Best for: Research workflows that need web, news, image, video, and place searches: it exposes those tools alongside local search, LLM-context retrieval, and summarization.

  It exposes eight tools covering web, local, video, image, news, and place searches, LLM context retrieval, and AI summarization through the Brave Search API, and supports both STDIO and HTTP transports. Before choosing it, note that full local search capabilities and extra snippets require a Brave Search API Pro plan.

  Score 94.6: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars80
    • npm downloads92
    • 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
  • Momentum91 / 100 · weight 14%
    • Stars gained, relative to size95
    • Stars gained, absolute79
    • npm download trend100
  • Tool quality83 / 100 · weight 13%
    • Tool description quality75
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  94.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  94.6

• 2

  SearXNG Server

  Community favourite

  ihor-sokoliuk/mcp-searxng ↗

  Best for: Teams already running a SearXNG instance who need search and page reading: it exposes two tools, one for web search and one for URL-to-markdown.

  It exposes two tools: searxng_web_search, which queries SearXNG and returns results with title, URL, and content snippet, and web_url_read, which fetches a URL and returns its text converted to markdown. It does not install SearXNG itself, so it requires an existing SearXNG instance with JSON search enabled, either one the operator runs or one they trust.

  Score 94.5: show every number behind it

  • Adoption98 / 100 · weight 40%
    • GitHub stars78
    • npm downloads86
    • 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
  • Momentum77 / 100 · weight 14%
    • Stars gained, relative to size82
    • Stars gained, absolute72
    • npm download trend75
  • 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

  94.5

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  94.5

• 3

  DuckDuckGo MCP Server

  Community favourite

  nickclyde/duckduckgo-mcp-server ↗

  Best for: Research sessions that need DuckDuckGo results and readable page text: it exposes search, fetch_content, and expand_link tools for queries, extraction, and ref:// expansion.

  The server exposes three tools: search for DuckDuckGo results, fetch_content for page-text extraction, and expand_link for converting shortened ref:// tokens back into full URLs; it documents stdio as the default transport plus SSE and Streamable HTTP. The documented quick-start path uses uvx to run the PyPI package, so that Python tooling is required before an MCP client can launch it.

  Score 93.7: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars80
    • PyPI downloads91
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade100
    • Commit cadence65
  • Momentum79 / 100 · weight 14%
    • Stars gained, relative to size72
    • Stars gained, absolute70
    • PyPI download trend100
  • Tool quality100 / 100 · weight 13%
    • Tool description quality93
    • 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

  93.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  93.7

• 4

  Perplexity API Platform MCP Server

  Community favourite

  perplexityai/modelcontextprotocol ↗

  Best for: Assistants that need live web answers: it offers four tools spanning ranked search, chat, reasoning, and deep research.

  The server exposes four tools (perplexity_search, perplexity_ask, perplexity_reason, perplexity_research) that route requests to Perplexity's Search and Agent APIs, returning ranked results with titles and URLs or message-based completions. Using it requires a Perplexity API key, and local installs run through the @perplexity-ai/mcp-server npm package or the hosted endpoint at https://api.perplexity.ai/mcp.

  Score 89.9: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars85
    • npm downloads95
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum73 / 100 · weight 14%
    • Stars gained, relative to size62
    • Stars gained, absolute73
    • npm download trend92
  • 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

  89.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  89.9

• 5

  Google Search Console MCP

  Community favourite

  AminForou/mcp-gsc ↗

  Best for: SEO professionals querying an existing Google Search Console property in natural language: it documents search analytics, URL inspection, and sitemap tools.

  The server connects Google Search Console to MCP-compatible clients and documents tools for listing properties, retrieving search analytics, comparing periods, inspecting URLs, and managing sitemaps. It assumes access to a Google Search Console property and an OAuth browser login; without authorized credentials, its analytics, inspection, and sitemap tools cannot be used.

  Score 88.8: show every number behind it

  • Adoption95 / 100 · weight 40%
    • GitHub stars83
    • PyPI downloads82
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance82 / 100 · weight 24%
    • Last commit touching this server100
      dated from the last commit on the default branch, re-read from GitHub at publication; the stored date would have published 51 days ago
    • Repository maintenance grade55
    • Commit cadence65
  • Momentum95 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute98
    • PyPI download trend81
  • Tool quality68 / 100 · weight 13%
    • Tool description quality60
    • 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

  88.8

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  88.8

• 6

  Tavily MCP Server

  Community favourite

  tavily-ai/tavily-mcp ↗

  Best for: Teams needing live web search plus page extraction, crawling, and site mapping: it exposes four tools covering search, extract, crawl, and map.

  Tavily MCP Server exposes search, extract, crawl, and map tools for web search, page content retrieval, site crawling, and URL structure mapping, and it can run as a remote MCP endpoint using a Tavily API key or OAuth. Choosing it requires a Tavily API key, supplied in the remote URL or Authorization header, or OAuth authentication with a compatible client.

  Score 84.9: show every number behind it

  • Adoption92 / 100 · weight 40%
    • GitHub stars85
    • npm downloads46
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum63 / 100 · weight 14%
    • Stars gained, relative to size63
    • Stars gained, absolute72
    • npm download trend50
  • Tool quality76 / 100 · weight 13%
    • Tool description quality68
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  84.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  84.9

• 7

  Google Search Console MCP Server

  Community favourite

  Suganthan-Mohanadasan/Suganthans-GSC-MCP ↗

  Best for: Analysing a site's own Google Search Console data inside Claude: 29 tools for quick wins, traffic drops, indexing checks and content decay.

  It is an MCP server for Google Search Console that exposes 29 tools covering search analytics queries, indexing status inspection, sitemap listing, alert checks, markdown report generation, image search analysis, and Indexing API submissions. Choosing it means supplying Google credentials first, either OAuth or a service account with access to the relevant Search Console properties, and running the Node package locally so data passes only between that machine and Google.

  Score 84.4: show every number behind it

  • Adoption74 / 100 · weight 40%
    • GitHub stars56
    • npm downloads66
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum89 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute64
    • npm download trend100
  • 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

  84.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  84.4

• 8

  open-webSearch

  Community favourite

  Aas-ee/open-webSearch ↗

  Best for: Searching the web without API keys across multiple engines and fetching articles or GitHub READMEs: it exposes a multi-engine search tool and dedicated fetch tools.

  It documents an MCP server, CLI, and local daemon with five tools: a multi-engine search tool and fetch tools for linux.do, CSDN, GitHub README, and Juejin content. The README lists linux.do search as temporarily unsupported, so that search route should not be relied on.

  Score 81.4: show every number behind it

  • Adoption82 / 100 · weight 40%
    • GitHub stars82
    • npm downloadsnot measured
      npm names no repository for open-websearch, so its downloads cannot be attributed
    • 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
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size56
    • Stars gained, absolute64
    • npm 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

  81.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  81.4

• 9

  Kagi MCP Server

  Community favourite

  kagisearch/kagimcp ↗

  Best for: Answering questions that need current web information in an MCP client: it exposes Kagi search/fetch and page extraction tools.

  The server exposes kagi_search_fetch for Kagi web, news, video, podcast, and image search and kagi_extract for fetching a page's content as markdown, and it documents a hosted HTTP endpoint plus local uvx setup. Before choosing it, note that it requires a Kagi API key (KAGI_API_KEY for local use or Bearer HTTP authentication for the hosted server), and OAuth2 is not supported yet.

  Score 77.9: show every number behind it

  • Adoption69 / 100 · weight 40%
    • GitHub stars69
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance88 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence65
  • Momentum66 / 100 · weight 14%
    • Stars gained, relative to size73
    • Stars gained, absolute55
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality85 / 100 · weight 13%
    • Tool description quality77
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  77.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  77.9

• 10

  Perplexity Web MCP

  Community favourite

  jacob-bd/perplexity-web-mcp ↗

  Best for: AI agents that need Perplexity web account answers with quota-aware model routing and saved threads: it exposes smart query, deep research, and thread tools.

  Perplexity Web MCP exposes 30 MCP tools for querying Perplexity models, running deep research and model council, checking usage, browsing threads, and managing authentication; the README also documents CLI and API server interfaces. It is unofficial and unsupported, depends on undocumented Perplexity web interface methods that may break, and requires Perplexity account authentication, with some models requiring a Max subscription.

  Score 76.0: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars58
    • PyPI downloads50
    • 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
  • Momentum74 / 100 · weight 14%
    • Stars gained, relative to size78
    • Stars gained, absolute45
    • PyPI download trend100
  • Tool quality51 / 100 · weight 13%
    • Tool description quality43
    • 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

  76.0

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  76.0

• 11

  Kindly Web Search MCP Server

  Community favourite

  Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server ↗

  Best for: AI coding assistants debugging against StackOverflow or GitHub Issues: it returns full conversations and structured content from those sources in a single call.

  Its README documents a web_search interface that returns titles, links, snippets, and best-effort Markdown page content, plus a get_content interface that returns page Markdown. The README lists Serper, SerpBase, Tavily, SearXNG, Sofya, You.com, and Serply as supported search providers with fallback, so search setup depends on one of those providers.

  Score 73.8: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars65
    • 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
  • Momentum43 / 100 · weight 14%
    • Stars gained, relative to size47
    • Stars gained, absolute37
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      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

  73.8

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  73.8

• 12

  Exa MCP Server

  Community favourite

  exa-labs/exa-mcp-server ↗

  Best for: Real-time web research that needs company, LinkedIn, and code-context searches: it exposes dedicated tools for those plus a start/check deep research workflow.

  It connects MCP clients to Exa's hosted endpoint and exposes eight tools for web search, page crawling, company and LinkedIn research, code-context lookup, and a start/check deep research workflow. Before choosing it, note the dependency on Exa's hosted MCP endpoint or the exa-mcp-server npm package, plus the README's direction to obtain an Exa API key.

  Score 72.0: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars93
    • npm downloads92
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum77 / 100 · weight 14%
    • Stars gained, relative to size61
    • Stars gained, absolute84
    • npm download trend100
  • 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

  92.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  72.0

• 13

  google-meta-ads-ga4-mcp

  Community favourite

  irinabuht12-oss/google-ads-meta-ads-mcp ↗

  Best for: Teams managing Google Ads, Meta Ads, GA4 and Search Console in one chat: it documents a hosted remote MCP with OAuth login and approval-gated writes.

  The README documents a hosted remote MCP endpoint for Google Ads, Meta Ads, GA4, and Google Search Console, connected through Google or Facebook OAuth login and approval-gated changes to budgets, bids, and negatives. It requires signing in with the Google or Facebook account that owns the ads and using the hosted Ryze connector endpoint.

  Score 70.8: show every number behind it

  • Adoption96 / 100 · weight 40%
    • GitHub stars96
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum100 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      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

  90.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  70.8

• 14

  Google Search Console MCP Server

  Community favourite

  ahonn/mcp-server-gsc ↗

  Best for: For querying Google Search Console performance and managing sitemaps, it exposes eight tools for search analytics, quick wins, index inspection, and sitemap operations.

  The server connects to Google Search Console and exposes eight tools for listing sites, querying search analytics, detecting quick wins, inspecting index status, and listing, getting, or submitting sitemaps. It assumes a Google Cloud project with the Search Console API enabled, service account credentials, and property administrator access for that service account.

  Score 66.2: show every number behind it

  • Adoption61 / 100 · weight 40%
    • GitHub stars61
    • npm downloadsnot measured
      npm names no repository for mcp-server-gsc, so its downloads cannot be attributed
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance76 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade80
    • Commit cadence40
  • Momentum42 / 100 · weight 14%
    • Stars gained, relative to size47
    • Stars gained, absolute33
    • npm download trendnot measured
      no download history for the selected registry
  • 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

  66.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  66.2

• 15

  Google Search MCP Server

  Community favourite

  mixelpixx/Nimrod ↗

  Best for: Claude users needing Google search plus webpage extraction in one MCP connection: it documents google_search, extract_webpage_content, extract_multiple_webpages, and research_topic.

  Nimrod documents google_search, extract_webpage_content, extract_multiple_webpages, and research_topic, and it can be connected as a hosted MCP endpoint or installed as a local desktop package. The hosted endpoint requires email sign-in from Claude.ai/Desktop or a Bearer key from Claude Code, and search/research calls consume credits while webpage extraction is free.

  Score 63.7: show every number behind it

  • Adoption60 / 100 · weight 40%
    • GitHub stars60
    • npm downloadsnot measured
      npm names no repository for google-search-mcp, so its downloads cannot be attributed
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance69 / 100 · weight 24%
    • Last commit touching this server88
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 34 days ago, which counts every ref; the stored date would have published 34 days ago
    • Repository maintenance grade30
    • Commit cadence65
  • Momentum30 / 100 · weight 14%
    • Stars gained, relative to size34
    • Stars gained, absolute24
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈76 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • 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

  63.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  63.7

• 16

  mcpsurfr

  Community favourite

  nkapila6/mcpsurfr ↗

  Best for: Deep research across several search terms on a local MCP setup: it exposes four tools for passage search, full-page retrieval, URL reading, and multi-term research.

  mcpsurfr is a local web search MCP server with four tools: search returns answering passages, rag_search_ddgs returns full pages as text, read_url reads a known HTML or PDF URL, and deep_research searches several terms across backends with local re-ranking. It is published on PyPI as mcpsurfr and documented installs use uvx or Docker (there is no npm package), so setup assumes uvx or Docker on the local machine.

  Score 63.1: show every number behind it

  • Adoption63 / 100 · weight 40%
    • GitHub stars55
    • PyPI downloads53
    • 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
  • Momentum82 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute55
    • PyPI 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

  80.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  63.1

• 17

  searxNcrawl

  Community favourite

  DasDigitaleMomentum/searxNcrawl ↗

  Best for: Teams running their own SearXNG instance: it exposes search, crawl and crawl_site tools, and needs no API key with SearXNG.

  searxNcrawl exposes three tools: search queries the configured providers, SearXNG and/or You.com, in parallel and merges the results, while crawl turns one or more URLs into Markdown or JSON and crawl_site walks a whole site from a seed URL. The search tool requires at least one configured provider, a SearXNG instance with JSON output enabled 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

• 18

  Search Console MCP

  Community favourite

  saurabhsharma2u/search-console-mcp ↗

  Best for: SEO teams querying Google Search Console and Bing performance from an agent: it exposes 25 tools covering analytics queries, indexing inspection, and sitemap management.

  Search Console MCP is a server that exposes 25 tools for querying Google Search Console, Bing Webmaster Tools, GA4, and AdSense data, alongside sitemap submission, URL indexing requests, page inspection, PageSpeed analysis, and schema validation. Setup stays read-only by default: sitemap and site mutation tools require an explicit webmasters write scope, and AdSense reporting needs approval of a separate adsense.readonly OAuth scope that supports user OAuth only, not service accounts.

  Score 61.5: show every number behind it

  • Adoption67 / 100 · weight 40%
    • GitHub stars63
    • npm downloads31
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum86 / 100 · weight 14%
    • Stars gained, relative to size97
    • Stars gained, absolute58
    • npm download trend100
  • Tool quality58 / 100 · weight 13%
    • Tool description quality50
    • 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

  78.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.5

• 19

  Jina AI Remote MCP Server

  Community favourite

  jina-ai/MCP ↗

  Best for: When an assistant needs current web search plus URL-to-markdown extraction, screenshots, arXiv/SSRN/image search, and reranking, this remote MCP endpoint exposes those tools.

  Jina AI Remote MCP Server connects to Jina's Reader, Search, Embeddings, and Reranker APIs through tools such as read_url, search_web, search_arxiv, search_ssrn, search_images, capture_screenshot_url, sort_by_relevance, deduplicate_strings, and extract_pdf. Before choosing it, note that search_web, arXiv/SSRN/image search, reranking, deduplication, and PDF extraction require a Jina API key, while clients without remote MCP support need the mcp-remote proxy.

  Score 61.3: show every number behind it

  • Adoption74 / 100 · weight 40%
    • GitHub stars74
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum69 / 100 · weight 14%
    • Stars gained, relative to size73
    • Stars gained, absolute62
    • 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 integrates100

  Weighted mean of the five

  78.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.3

• 20

  Google Search Console MCP Server

  Emerging

  onlymoein/google-search-console-mcp ↗

  Best for: Site owners debugging indexing and traffic changes on their own Search Console property: it exposes URL inspection, indexing audits and explain_change alongside sitemap tools.

  The server runs locally against the Google Search Console API and exposes 22 tools covering search analytics queries, period comparison, URL inspection, indexing audits, search appearances and sitemap and property management, with analytics results returned as named fields plus the exact request sent to Google. Before choosing it, note that it requires a Google Cloud OAuth client or service account with the Search Console API enabled, an existing property the account can access, and uv to run the PyPI package open-gsc-mcp; write tools can be turned off with GSC_ENABLE_WRITES=0.

  Score 60.8: show every number behind it

  • Adoption44 / 100 · weight 40%
    • GitHub stars26
    • PyPI downloads41
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum77 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute42
    • PyPI download trendnot measured
      no download history for the selected registry
  • Tool quality83 / 100 · weight 13%
    • Tool description quality75
    • 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

  71.5

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  60.8

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 Scraping 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