Skip to main content
Glama
MCP Web Research Server

MCP Web Research Server

by chuanmingliu

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 with no overlap: search_google finds web pages, visit_page loads and extracts content from a specific URL, and take_screenshot captures the current page. An agent can easily distinguish between these functions without confusion.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (search_google, take_screenshot, visit_page), making them predictable and readable. There are no deviations or mixed conventions in the naming style.

    Tool Count3/5

    With only 3 tools, the set feels thin for a 'Web Research Server' as it lacks operations like saving results, navigating pages, or handling multiple tabs. While the tools cover basic web interactions, the count is borderline low for comprehensive research tasks.

    Completeness3/5

    The tools provide core functions (search, visit, screenshot) but leave notable gaps for a research server, such as no ability to interact with page elements, manage sessions, or export data. Agents can work around this for simple tasks, but advanced research workflows will be limited.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers