MCP Server for Stealth Web Search and Fetching
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| websearchB | Search the web with DuckDuckGo or Google and return numbered results with titles, URLs and snippets. |
| webfetchA | Fetch a web page in a JavaScript-capable stealth browser and return its main content as Markdown, with images, scripts and styles stripped. Long output is paginated. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: websearch performs discovery (querying DuckDuckGo/Google), while webfetch retrieves and renders a specific URL. There is no plausible overlap or confusion between searching and fetching.
Both names follow the identical 'web' + verb convention (websearch, webfetch) in consistent lowercase with no separator. The pattern is fully predictable across the set.
Two tools is minimal but well-matched to a narrow search-and-fetch domain, where each tool maps to a core operation. It is slightly thin (no batch or pagination-control tool), but nothing feels redundant.
Search plus JavaScript-capable fetch with pagination covers the essential lifecycle of web retrieval, and the fetch tool handles content normalization. Minor gaps exist around result-count/format control, but core workflows are fully served.