mcp-web-tools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PERPLEXITY_API_KEY | No | Perplexity Search API key to prioritize their fresh, citation-rich index | |
| BRAVE_SEARCH_API_KEY | No | Brave Search API key for enhanced search results |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_webA | |
| fetch_urlB | Universal content loader that fetches and processes content from any URL. Automatically detects content type (webpage, PDF, or image) based on URL. |
| view_websiteA | Capture and return a rendered screenshot of a website. Helpful when not just the data but also the visuals are relevant. |
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 3 tools
Each tool has a distinct purpose: fetching URL content, performing web search, and capturing website screenshots. No overlap in functionality.
All tool names follow a consistent verb_noun pattern with underscores (fetch_url, search_web, view_website), making them predictable and easy to understand.
Three tools is appropriate for a web utilities server, covering the core needs without being too minimal or excessive.
The tool set covers key web interactions: fetching content, searching, and visual capture. A minor gap might be the lack of a dedicated tool for downloading files or parsing specific formats, but fetch_url addresses most content types.