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: 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.
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.
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.
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.