Skip to content
Back to search

mcp-webresearch

MCP web research server (give Claude real-time info from the web)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/mzxrai--mcp-webresearch/badge.svg)](/listings/mzxrai--mcp-webresearch)

HTML

<a href="/listings/mzxrai--mcp-webresearch"><img src="/api/listings/mzxrai--mcp-webresearch/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

First, ensure you've downloaded and installed the [Claude Desktop app](https://claude.ai/download) and you have npm installed.

Next, add this entry to your `claude_desktop_config.json` (on Mac, found at `~/Library/Application\ Support/Claude/claude_desktop_config.json`):

{
  "mcpServers": {
    "webresearch": {
      "command": "npx",
      "args": ["-y", "@mzxrai/mcp-webresearch@latest"]
    }
  }
}

This config allows Claude Desktop to automatically start the web research MCP server when needed.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 131 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Web Research Server
  2. A Model Context Protocol (MCP) server for web research.
  3. Bring real-time info into Claude and easily research any topic.
  4. ## Features
  5. - Google search integration
  6. - Webpage content extraction
  7. - Research session tracking (list of visited pages, search queries, etc.)
  8. - Screenshot capture
  9. ## Prerequisites
  10. - [Node.js](https://nodejs.org/) >= 18 (includes `npm` and `npx`)
  11. - [Claude Desktop app](https://claude.ai/download)
  12. ## Installation
  13. First, ensure you've downloaded and installed the [Claude Desktop app](https://claude.ai/download) and you have npm installed.
  14. Next, add this entry to your `claude_desktop_config.json` (on Mac, found at `~/Library/Application\ Support/Claude/claude_desktop_config.json`):
  15. ```json
  16. {
  17. "mcpServers": {
  18. "webresearch": {
  19. "command": "npx",
  20. "args": ["-y", "@mzxrai/mcp-webresearch@latest"]
  21. }
  22. }
  23. }
  24. ```
  25. This config allows Claude Desktop to automatically start the web research MCP server when needed.
  26. ## Usage
  27. Simply start a chat with Claude and send a prompt that would benefit from web research. If you'd like a prebuilt prompt customized for deeper web research, you can use the `agentic-research` prompt that we provide through this package. Access that prompt in Claude Desktop by clicking the Paperclip icon in the chat input and then selecting `Choose an integration` → `webresearch` → `agentic-research`.
  28. <img src="https://i.ibb.co/N6Y3C0q/Screenshot-2024-12-05-at-11-01-27-PM.png" alt="Example screenshot of web research" width="400"/>
  29. ### Tools
  30. 1. `search_google`
  31. - Performs Google searches and extracts results
  32. - Arguments: `{ query: string }`
  33. 2. `visit_page`
  34. - Visits a webpage and extracts its content
  35. - Arguments: `{ url: string, takeScreenshot?: boolean }`
  36. 3. `take_screenshot`
  37. - Takes a screenshot of the current page
  38. - No arguments required
  39. ### Prompts
  40. #### `agentic-research`
  41. A guided research prompt that helps Claude conduct thorough web research. The prompt instructs Claude to:
  42. - Start with broad searches to understand the topic landscape
  43. - Prioritize high-quality, authoritative sources
  44. - Iteratively refine the research direction based on findings
  45. - Keep you informed and let you guide the research interactively
  46. - Always cite sources with URLs
  47. ### Resources
  48. We expose two things as MCP resources: (1) captured webpage screenshots, and (2) the research session.
  49. #### Screenshots
  50. When you take a screenshot, it's saved as an MCP resource. You can access captured screenshots in Claude Desktop via the Paperclip icon.
  51. #### Research Session
  52. The server maintains a research session that includes:
  53. - Search queries
  54. - Visited pages
  55. - Extracted content
  56. - Screenshots
  57. - Timestamps
  58. ### Suggestions
  59. For the best results, if you choose not to use the `agentic-research` prompt when doing your research, it may be helpful to suggest high-quality sources for Claude to use when researching general topics. For example, you could prompt `news today from reuters or AP` instead of `news today`.
  60. ## Problems
  61. This is very much pre-alpha code. And it is also AIGC, so expect bugs.
  62. If you run into issues, it may be helpful to check Claude Desktop's MCP logs:
  63. ```bash
  64. tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
  65. ```
  66. ## Development
  67. ```bash
  68. # Install dependencies
  69. pnpm install
  70. # Build the project
  71. pnpm build
  72. # Watch for changes
  73. pnpm watch
  74. # Run in development mode
  75. pnpm dev
  76. ```
  77. ## Requirements
  78. - Node.js >= 18
  79. - Playwright (automatically installed as a dependency)
  80. ## Verified Platforms
  81. - [x] macOS
  82. - [ ] Linux
  83. ## License
  84. MIT
  85. ## Author
  86. [mzxrai](https://github.com/mzxrai)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.