Skip to main content
Glama
chuanmingliu

MCP Web Research Server

by chuanmingliu

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
search_googleC

Search Google for a query

visit_pageC

Visit a webpage and extract its content

take_screenshotB

Take a screenshot of the current page

Prompts

Interactive templates invoked by user choice

NameDescription
agentic-researchConduct iterative web research on a topic, exploring it thoroughly through multiple steps while maintaining a dialogue with the user

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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 issues