MCP Web Research Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Name | Description |
|---|---|
| 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
| Name | Description |
|---|---|
| agentic-research | Conduct 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
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
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.
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.
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.
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.