Skip to main content
Glama
MCP Web Research Server

MCP Web Research Server

by mzxrai

MCP Web Research Server

A Model Context Protocol (MCP) server for web research.

Bring real-time info into Claude and easily research any topic.

Features

  • Google search integration

  • Webpage content extraction

  • Research session tracking (list of visited pages, search queries, etc.)

  • Screenshot capture

Related MCP server: MCP Web Research Server

Prerequisites

Installation

First, ensure you've downloaded and installed the Claude Desktop app 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.

Usage

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.

Tools

  1. search_google

    • Performs Google searches and extracts results

    • Arguments: { query: string }

  2. visit_page

    • Visits a webpage and extracts its content

    • Arguments: { url: string, takeScreenshot?: boolean }

  3. take_screenshot

    • Takes a screenshot of the current page

    • No arguments required

Prompts

agentic-research

A guided research prompt that helps Claude conduct thorough web research. The prompt instructs Claude to:

  • Start with broad searches to understand the topic landscape

  • Prioritize high-quality, authoritative sources

  • Iteratively refine the research direction based on findings

  • Keep you informed and let you guide the research interactively

  • Always cite sources with URLs

Resources

We expose two things as MCP resources: (1) captured webpage screenshots, and (2) the research session.

Screenshots

When you take a screenshot, it's saved as an MCP resource. You can access captured screenshots in Claude Desktop via the Paperclip icon.

Research Session

The server maintains a research session that includes:

  • Search queries

  • Visited pages

  • Extracted content

  • Screenshots

  • Timestamps

Suggestions

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.

Problems

This is very much pre-alpha code. And it is also AIGC, so expect bugs.

If you run into issues, it may be helpful to check Claude Desktop's MCP logs:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Development

# Install dependencies
pnpm install

# Build the project
pnpm build

# Watch for changes
pnpm watch

# Run in development mode
pnpm dev

Requirements

  • Node.js >= 18

  • Playwright (automatically installed as a dependency)

Verified Platforms

  • macOS

  • Linux

License

MIT

Author

mzxrai

Available Tools

3 tools
search_googleC

Search Google for a query

Inputs: query (required).

take_screenshotB

Take a screenshot of the current page

Inputs: no named parameters.

visit_pageC

Visit a webpage and extract its content

Inputs: url (required), takeScreenshot.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: search_google finds web pages, visit_page loads and extracts content from a specific URL, and take_screenshot captures visual data from the current page. There is no overlap in functionality, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All three tools follow a consistent verb_noun naming pattern (search_google, take_screenshot, visit_page) with clear, descriptive verbs that align with their actions. The naming is uniform and predictable across the set.

    Tool Count4/5

    Three tools is a reasonable count for a web research server, covering core actions like searching, visiting, and capturing pages. It might feel slightly thin for broader research tasks (e.g., no navigation or interaction tools), but it is well-scoped for basic operations.

    Completeness3/5

    The tools cover key web research steps: search, visit, and screenshot. However, there are notable gaps such as no navigation tools (e.g., click, scroll) or interaction capabilities (e.g., fill forms), which could limit more complex research workflows. The surface is functional but not fully comprehensive.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers