Ext Ops Panel
Open dashboard
Comparison

web-researcher vs io.github.tavily-ai/tavily-mcp

web-researcher is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑17.

web-researcher is a plugin bundle for AI coding tools published by Daniel Worthington-Bodart. No marketplace we read lists it any more. io.github.tavily-ai/tavily-mcp is an MCP server published by tavily-ai. Marketplaces we read that list it: 3 (Official MCP Registry, Docker MCP Catalog, npm registry (MCP servers)). As of our marketplace pass on 2026-10-30. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceweb-researcherio.github.tavily-ai/tavily-mcp
Community marketplace danielbodart/claude-code-plugins Removed on 2026-10-17
Version: 1.0.75
Forks (GitHub): 0
Stars (GitHub): 3
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.2.15
Downloads/month (npm): 89 437
Downloads/week (npm): 11 971
Forks (GitHub): 307
Stars (GitHub): 2 462
Not marked · First seen
Docker MCP Catalog Not listed Listed
Version: sha256:e8bbe2860c85
Forks (GitHub): 307
Pulls (Docker Hub): 56 962
Stars (Docker Hub): 8
Stars (GitHub): 2 462
Not marked · First seen
npm registry (MCP servers) Not listed Listed
Version: 0.2.22
Downloads/month (npm): 89 437
Downloads/week (npm): 11 971
Forks (GitHub): 307
Stars (GitHub): 2 462
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

web-researcher vs io.github.tavily-ai/tavily-mcp
Factweb-researcherno longer listed · io.github.tavily-ai/tavily-mcp
Marketplaces that list it (differs)03
Stars (GitHub) (differs)32 462
Pulls (Docker Hub) (differs)No figure on Docker Hub56 962
Forks (GitHub) (differs)0307
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (tavily-mcp)
Transport (differs)Not statedstdio
Tools it declares (differs)Not published5
Environment variables it asks for (differs)Not published2, secrets among them: 1
Parts of the bundle (differs)1Not a bundle
LicenceMITMIT
Repository (differs)github.com/danielbodart/claude-code-pluginsgithub.com/tavily-ai/tavily-mcp
Changes in the last 7 days00
First seen (differs)2026-10-152026-10-11

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of web-researcher

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • scout

    Web search and content fetching with privacy-aware tool selection. Turns vague questions into optimized multi-engine queries, evaluates result quality, and re-searches when…

    by shidoyu · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

  • web-search-hardened-skills

    Search engines, web scrapers, and browser automation.

    by faberlens · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • Robin: AI-Powered Dark Web OSINT

    Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.

    by apurvsinghgautam · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • exa

    Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…

    by exa-labs · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Official MCP Registry, Docker MCP Catalog, Claude: knowledge-work-plugins · Describes nearly the same job

  • firecrawl

    Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, crawl entire sites, search the web, and…

    by firecrawl · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • 1cent Web Intelligence for AI Agents

    SSRF-safe web intelligence: 4 outcomes, 43 paid x402 tools, 3 free tools and a URL preview.

    by maxzoa.ru · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

web-researcher

In its own words, on Community GitHub marketplaces:

Deep web research agent that finds and synthesizes information from multiple sources

io.github.tavily-ai/tavily-mcp

In its own words, on Official MCP Registry:

MCP server for advanced web search using Tavily

How to run each

web-researcher

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

io.github.tavily-ai/tavily-mcp As a local MCP server: npm package

Claude Code
claude mcp add --env "TAVILY_API_KEY=<YOUR_TAVILY_API_KEY>" --transport stdio tavily-mcp -- npx -y tavily-mcp

Requires: TAVILY_API_KEY (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

The marketplaces of web-researcher publish no list of tools, so we do not compare tools.

Settings each asks for

The marketplaces of web-researcher publish no settings it asks for, so we do not compare settings.

What it can do: web-researcher · What it can do: io.github.tavily-ai/tavily-mcp · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built